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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    户
    -0.07
    оступ
    -0.06
    FORCE
    -0.06
    HEME
    -0.06
    Lambda
    -0.06
    asured
    -0.06
    抗
    -0.06
     обор
    -0.06
     workspace
    -0.06
    ropa
    -0.06
    POSITIVE LOGITS
    .UseFont
    0.06
     Lunar
    0.06
    yst
    0.06
     Telephone
    0.06
     sparse
    0.06
    editable
    0.06
    .bc
    0.06
    /******/↵
    0.06
    (Db
    0.06
     MISS
    0.06
    Act Density 0.001%

    No Known Activations