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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    akis
    -0.08
    enas
    -0.07
    (Employee
    -0.07
    asis
    -0.07
    Node
    -0.07
    Original
    -0.06
    NET
    -0.06
     Nurse
    -0.06
    _d
    -0.06
     dancing
    -0.06
    POSITIVE LOGITS
    שוב
    0.07
    哈尔
    0.07
    +=(
    0.07
    힌
    0.07
    䓛
    0.07
    闽
    0.07
    .DOM
    0.06
    Sibling
    0.06
    付款
    0.06
    _rb
    0.06
    Act Density 0.003%

    No Known Activations