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

    Neuronpedia

    INDEX
    Explanations

    msgid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    naz
    -0.07
     caval
    -0.06
     kol
    -0.06
    .localization
    -0.06
    めて
    -0.06
     nob
    -0.06
    kud
    -0.06
    rawing
    -0.06
     vengeance
    -0.06
     INSTANCE
    -0.06
    POSITIVE LOGITS
     Address
    0.07
    025
    0.06
    edish
    0.06
     Федераль
    0.06
     imz
    0.06
     Ruth
    0.06
    (obj
    0.06
     primary
    0.06
     Valid
    0.06
    TW
    0.06
    Act Density 0.002%

    No Known Activations