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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISK
    -0.07
    ダー
    -0.07
    疫
    -0.07
    acists
    -0.07
    𝐲
    -0.07
    -width
    -0.06
     Ec
    -0.06
     sürec
    -0.06
    .ac
    -0.06
    ursed
    -0.06
    POSITIVE LOGITS
    _have
    0.07
     vertex
    0.07
     подпис
    0.07
    asmine
    0.07
    mall
    0.07
    藜
    0.07
     coax
    0.07
    \Component
    0.06
    箩
    0.06
    省公安
    0.06
    Act Density 0.001%

    No Known Activations