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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Span
    -0.07
     defer
    -0.06
    COD
    -0.06
    dek
    -0.06
    方
    -0.06
    (best
    -0.06
    オン
    -0.06
     Synopsis
    -0.06
     sensations
    -0.06
    _nodes
    -0.06
    POSITIVE LOGITS
    Little
    0.06
    ствует
    0.06
    _trip
    0.06
    alsex
    0.06
    ЕТ
    0.06
    Requires
    0.06
    ._
    0.06
    ٬
    0.06
    doesn
    0.06
    唯
    0.06
    Act Density 0.099%

    No Known Activations