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

    Neuronpedia

    INDEX
    Explanations

    template

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tháng
    -0.07
     Af
    -0.07
     Elf
    -0.07
     Benson
    -0.06
    KH
    -0.06
     Acc
    -0.06
     norsk
    -0.06
     DS
    -0.06
     invites
    -0.06
    سس
    -0.06
    POSITIVE LOGITS
    셒
    0.07
    ArgsConstructor
    0.07
    ribbon
    0.07
    מוזיאון
    0.07
    .TimeUnit
    0.07
     Jump
    0.07
    海峡
    0.07
    .sub
    0.07
    Exposed
    0.07
     Sporting
    0.07
    Act Density 0.002%

    No Known Activations