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

    Neuronpedia

    INDEX
    Explanations

    gratitude and privilege

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    松
    -0.06
    uyen
    -0.06
    étique
    -0.06
    Cu
    -0.06
     �
    -0.06
     後
    -0.06
    .putString
    -0.06
    whereIn
    -0.06
     headphones
    -0.06
     التع
    -0.06
    POSITIVE LOGITS
    Master
    0.08
     слишком
    0.07
    ินท
    0.07
     AFF
    0.07
     získ
    0.06
     дот
    0.06
     kole
    0.06
     đang
    0.06
     hasattr
    0.06
     Assuming
    0.06
    Act Density 0.041%

    No Known Activations