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

    Neuronpedia

    INDEX
    Explanations

    symbols or bullet points that indicate lists or important items

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

    Sentences containing bullet points

    np_acts-logits-general · gemini-2.0-flash

    found, female, washable, in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    -0.77
    ING
    -0.77
    izing
    -0.75
    OfBirth
    -0.71
    ******/
    -0.70
    colin
    -0.69
    ing
    -0.68
    pax
    -0.66
     Pax
    -0.66
     Garg
    -0.65
    POSITIVE LOGITS
    er
    1.37
    ••
    1.23
    .•
    1.19
    ••••
    1.13
    °•
    1.06
    •••
    1.02
    ER
    1.01
    ~•
    1.00
    erà
    0.98
     ••
    0.96
    Act Density 0.281%

    No Known Activations