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

    Neuronpedia

    INDEX
    Explanations

    small

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    small
    -0.96
    theless
    -0.77
    tiny
    -0.75
    large
    -0.71
    stoke
    -0.67
    Chham
    -0.60
     ProtoMessage
    -0.57
    smaller
    -0.56
     amitié
    -0.55
    sal
    -0.54
    POSITIVE LOGITS
    ьаж
    0.57
     Wikispecies
    0.55
    djangoproject
    0.54
    issi
    0.49
     Money
    0.49
    ⓧ
    0.48
     money
    0.48
     Justice
    0.48
    ifrance
    0.47
     and
    0.47
    Act Density 0.639%

    No Known Activations