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

    Neuronpedia

    INDEX
    Explanations

    passwords and security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GPIO
    -0.07
     Mend
    -0.07
    _delta
    -0.07
     Spider
    -0.06
     prefab
    -0.06
    .INPUT
    -0.06
    라이
    -0.06
    _schema
    -0.06
     chips
    -0.06
    CLS
    -0.06
    POSITIVE LOGITS
     edilen
    0.07
     */↵↵↵↵
    0.06
     �
    0.06
     Truy
    0.06
    แทน
    0.06
    ug
    0.06
    Ref
    0.06
     alex
    0.06
    vais
    0.06
    */↵↵
    0.06
    Act Density 0.043%

    No Known Activations