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

    Neuronpedia

    INDEX
    Explanations

    Japanese characters and numbers

    oai_token-act-pair · gemini-2.0-flash

    Numbers, prices, and foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.69
    bibfield
    -0.68
     myſelf
    -0.65
    bibinfo
    -0.62
     mourut
    -0.58
     auroit
    -0.56
     againſt
    -0.56
    seamnă
    -0.55
     Theſe
    -0.54
     étoit
    -0.54
    POSITIVE LOGITS
     تز
    0.59
    歳の
    0.58
     שוליים
    0.58
    億円
    0.56
    CppCodeGen
    0.56
     AttributeSet
    0.56
    年後
    0.56
    万円
    0.55
    歳
    0.54
    月から
    0.53
    Act Density 1.340%

    No Known Activations