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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (foo
    -0.07
     toplumsal
    -0.07
     compensated
    -0.07
     Kendrick
    -0.06
    getAs
    -0.06
    。如果
    -0.06
    旦
    -0.06
     कहन
    -0.06
     Initialization
    -0.06
     kir
    -0.06
    POSITIVE LOGITS
     redesigned
    0.06
     ци
    0.06
    سام
    0.06
    ív
    0.06
    Could
    0.06
    st
    0.06
     FontStyle
    0.06
    しょ
    0.06
    ippo
    0.06
    idges
    0.06
    Act Density 0.053%

    No Known Activations