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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating contemplation and evaluation

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

    associated with understanding or acknowledgement

    np_acts-logits-general · gemini-2.0-flash

    dawning of realization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.74
     تانيه
    -0.71
    buttonBar
    -0.67
    farwyddwr
    -0.67
     متعلقه
    -0.65
     löytyy
    -0.65
     dAtA
    -0.63
     cordially
    -0.63
    tagHelperRunner
    -0.61
    WithIOException
    -0.61
    POSITIVE LOGITS
     realization
    0.96
     realisation
    0.79
     realizing
    0.73
     reality
    0.72
     осозна
    0.69
     comprehend
    0.67
     realize
    0.67
     implications
    0.67
     realiz
    0.67
     realizes
    0.66
    Act Density 0.209%

    No Known Activations