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

    Neuronpedia

    INDEX
    Explanations

    probability letter calculations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pac
    -0.07
    ugas
    -0.07
    یره
    -0.06
    ності
    -0.06
    _EQUALS
    -0.06
    {\
    -0.06
     brainstorm
    -0.06
     stupidity
    -0.06
    /Set
    -0.06
     espa
    -0.06
    POSITIVE LOGITS
    退出
    0.07
    TARGET
    0.07
    each
    0.06
     перемен
    0.06
     Mutex
    0.06
    _message
    0.06
    ‌ده
    0.06
    _ZONE
    0.06
     SUBJECT
    0.06
     приготов
    0.06
    Act Density 0.003%

    No Known Activations