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

    Neuronpedia

    INDEX
    Explanations

    coding errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _voltage
    -0.07
     Dx
    -0.07
    _Handler
    -0.07
    קרה
    -0.07
    catalog
    -0.07
    嗓子
    -0.07
    _overflow
    -0.06
     권리
    -0.06
    ื่
    -0.06
     consulted
    -0.06
    POSITIVE LOGITS
    (parser
    0.07
    战略布局
    0.07
    _layer
    0.07
    .Pages
    0.07
    atically
    0.06
     Brian
    0.06
    拿下
    0.06
    Sal
    0.06
     purposes
    0.06
    可观
    0.06
    Act Density 0.005%

    No Known Activations