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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivi
    -0.07
    いい
    -0.06
    ptal
    -0.06
    ystone
    -0.06
    _factors
    -0.06
    rea
    -0.06
     Build
    -0.06
    rium
    -0.06
    RK
    -0.06
    งศ
    -0.05
    POSITIVE LOGITS
     дан
    0.07
     DPR
    0.07
    óln
    0.06
     Participant
    0.06
    .Should
    0.06
     '(
    0.06
     Да
    0.06
     položky
    0.06
     Можно
    0.06
    (Un
    0.06
    Act Density 0.052%

    No Known Activations