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

    Neuronpedia

    INDEX
    Explanations

    mentions of organizations and their actions, especially in a critical context

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

    numbers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TypedDataSet
    -0.52
     creș
    -0.47
     și
    -0.46
     enggak
    -0.45
     theaters
    -0.44
    ști
    -0.44
     ști
    -0.42
     theater
    -0.42
     Și
    -0.41
    și
    -0.40
    POSITIVE LOGITS
    COLOUR
    0.75
    colourful
    0.75
     favourite
    0.75
    Behaviour
    0.74
    favourite
    0.73
    Neighbour
    0.73
    Colour
    0.71
     randomised
    0.71
     tumour
    0.70
     colourful
    0.69
    Act Density 0.154%

    No Known Activations