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

    Neuronpedia

    INDEX
    Explanations

    service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    651
    -0.07
    while
    -0.06
    _second
    -0.06
    flow
    -0.06
    ола
    -0.06
    706
    -0.06
     Верхов
    -0.06
    绩
    -0.06
    DWORD
    -0.06
     конце
    -0.06
    POSITIVE LOGITS
    lexible
    0.06
     spices
    0.06
    uel
    0.06
    (System
    0.06
     awaited
    0.06
    dea
    0.06
    maid
    0.06
     Outputs
    0.06
     draws
    0.06
     Sultan
    0.06
    Act Density 0.096%

    No Known Activations