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

    Neuronpedia

    INDEX
    Explanations

    biography

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    رى
    -0.08
    ListModel
    -0.07
    �
    -0.07
     etk
    -0.07
     testament
    -0.07
     bolt
    -0.06
     pentru
    -0.06
     پخش
    -0.06
     obras
    -0.06
    Ye
    -0.06
    POSITIVE LOGITS
    _destroy
    0.06
    ่ะ
    0.06
    alu
    0.06
    iphers
    0.06
     tolerate
    0.06
     Indy
    0.06
     факти
    0.06
    (Unit
    0.06
    总
    0.06
     ±
    0.06
    Act Density 0.002%

    No Known Activations