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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _buckets
    -0.06
    but
    -0.06
     narc
    -0.06
    dur
    -0.06
     Müdür
    -0.06
    .Mod
    -0.06
     потому
    -0.06
    ��
    -0.06
    Ce
    -0.06
    емон
    -0.06
    POSITIVE LOGITS
    ision
    0.07
     bridge
    0.07
     místní
    0.07
     tag
    0.07
    няття
    0.06
     Structure
    0.06
    (dispatch
    0.06
     branch
    0.06
    ₀
    0.06
    gom
    0.06
    Act Density 0.002%

    No Known Activations