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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ardon
    -0.07
    Cover
    -0.07
     вы
    -0.07
     past
    -0.07
    saving
    -0.06
    よい
    -0.06
     lots
    -0.06
    很是
    -0.06
    concert
    -0.06
    üst
    -0.06
    POSITIVE LOGITS
     ANC
    0.07
    تعليم
    0.07
    灾难
    0.07
    electric
    0.07
    𝙘
    0.07
     reven
    0.06
    ręcz
    0.06
    碳
    0.06
     среди
    0.06
    /to
    0.06
    Act Density 0.012%

    No Known Activations