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

    Neuronpedia

    INDEX
    Explanations

    Foreign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jonathan
    -0.07
     fantasy
    -0.06
     Sellers
    -0.06
    ける
    -0.06
     erection
    -0.06
    We
    -0.06
    UCCEEDED
    -0.06
     licensed
    -0.06
    ستان
    -0.06
    _chk
    -0.06
    POSITIVE LOGITS
    (Main
    0.06
    .Lang
    0.06
    úb
    0.06
     tự
    0.06
    �
    0.06
    ONSE
    0.06
     سخ
    0.06
     самом
    0.06
    (InitializedTypeInfo
    0.06
     skal
    0.06
    Act Density 0.576%

    No Known Activations