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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ременно
    -0.07
    يرة
    -0.07
    Geometry
    -0.07
    baru
    -0.07
    ANDROID
    -0.06
     ταιν
    -0.06
    paginate
    -0.06
     mistakenly
    -0.06
     susp
    -0.06
    CLUS
    -0.06
    POSITIVE LOGITS
    agne
    0.07
    Ac
    0.06
    まで
    0.06
    476
    0.06
    148
    0.06
    052
    0.06
    TokenType
    0.06
    899
    0.06
     salv
    0.06
    501
    0.06
    Act Density 0.000%

    No Known Activations