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

    Neuronpedia

    INDEX
    Explanations

    _unlock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     статьи
    -0.07
    hibit
    -0.06
     určit
    -0.06
    apter
    -0.06
     lect
    -0.06
    灭
    -0.06
    ismatch
    -0.06
     평균
    -0.06
    _atual
    -0.06
    _qos
    -0.06
    POSITIVE LOGITS
    _unlock
    0.08
     Swap
    0.07
    ίθ
    0.07
     Turns
    0.07
    Every
    0.07
    fur
    0.06
    /↵↵↵
    0.06
    .UTC
    0.06
    .GetString
    0.06
    (KERN
    0.06
    Act Density 0.001%

    No Known Activations