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

    Neuronpedia

    INDEX
    Explanations

    position

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Prefs
    -0.07
    ween
    -0.06
    Ny
    -0.06
    emouth
    -0.06
    WX
    -0.06
    .hp
    -0.06
    ぬ
    -0.06
    getWindow
    -0.06
    WEEN
    -0.06
    _Read
    -0.06
    POSITIVE LOGITS
    .delivery
    0.07
     식
    0.06
    кус
    0.06
     zdrav
    0.06
     Moroccan
    0.06
    angered
    0.06
    .softmax
    0.06
    igital
    0.06
    /ph
    0.06
    /Getty
    0.06
    Act Density 0.011%

    No Known Activations