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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _iter
    -0.07
    _coef
    -0.07
    شاه
    -0.06
    ahren
    -0.06
    .Title
    -0.06
     folklore
    -0.06
    FullName
    -0.06
    _week
    -0.06
    .tencent
    -0.06
     Geometry
    -0.06
    POSITIVE LOGITS
     Invest
    0.07
    nis
    0.07
     лес
    0.06
     Russell
    0.06
    手を
    0.06
     camb
    0.06
     Rupert
    0.06
    embedded
    0.06
     Soft
    0.06
    Jets
    0.06
    Act Density 0.004%

    No Known Activations