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

    Neuronpedia

    INDEX
    Explanations

    instructions and suggestions for actions or behaviors

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

    have to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.52
    findpost
    -0.48
    Clik
    -0.48
    ftagPool
    -0.45
    DockStyle
    -0.45
     متعلقه
    -0.45
     GeoNames
    -0.45
    عرِّف
    -0.45
    ympto
    -0.44
    uggest
    -0.44
    POSITIVE LOGITS
     must
    0.56
     musí
    0.51
     måste
    0.50
    must
    0.47
     muszą
    0.47
    Must
    0.47
     Must
    0.46
     necesaria
    0.46
     trzeba
    0.44
     faudra
    0.44
    Act Density 0.152%

    No Known Activations