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

    Neuronpedia

    INDEX
    Explanations

    Section

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     participation
    -0.07
     StringUtils
    -0.07
     Norm
    -0.07
    izu
    -0.07
    Mass
    -0.06
    discord
    -0.06
    record
    -0.06
    closure
    -0.06
     Harrison
    -0.06
    NumberFormatException
    -0.06
    POSITIVE LOGITS
     lửa
    0.07
    _Syntax
    0.07
     הע
    0.07
     sof
    0.07
    中铁
    0.07
    ים
    0.06
    inho
    0.06
    orias
    0.06
     afr
    0.06
    .met
    0.06
    Act Density 0.009%

    No Known Activations