Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    language related to economic and political discussions regarding fiscal policies and discrimination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "a/an" or adjectives

    np_acts-logits-general · gemini-2.0-flash

    outcomes, challenge, pattern

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Analyse
    -0.73
     specialises
    -0.70
     specialise
    -0.70
     apologise
    -0.68
     finalised
    -0.66
    mappedBy
    -0.65
     summarised
    -0.64
     diarrhoea
    -0.64
     specialising
    -0.62
    colourful
    -0.61
    POSITIVE LOGITS
     calculus
    0.71
     lens
    0.66
     cadence
    0.60
     conversation
    0.58
    엇
    0.58
     trajectory
    0.57
     contours
    0.56
     path
    0.56
     playbook
    0.55
     animating
    0.55
    Act Density 0.387%

    No Known Activations