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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hardt
    -0.07
     official
    -0.07
     patient
    -0.07
    explicit
    -0.07
     possess
    -0.06
     enemies
    -0.06
    _signed
    -0.06
     женщин
    -0.06
     Explicit
    -0.06
     ум
    -0.06
    POSITIVE LOGITS
    ILER
    0.06
     czas
    0.06
    Sys
    0.06
    ΕΛ
    0.06
    pei
    0.06
    卓
    0.06
    Dist
    0.06
    SHARE
    0.06
     Powered
    0.06
    .Brand
    0.06
    Act Density 0.465%

    No Known Activations