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

    Neuronpedia

    INDEX
    Explanations

    handle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —if
    -0.06
     리스트
    -0.06
     Quyết
    -0.06
    ología
    -0.06
    bf
    -0.06
     Essays
    -0.06
     Manchester
    -0.06
    some
    -0.05
    =h
    -0.05
    Ρ
    -0.05
    POSITIVE LOGITS
    DialogContent
    0.07
     요
    0.07
     역시
    0.07
    로그램
    0.06
    aight
    0.06
    �
    0.06
    =open
    0.06
    ковые
    0.06
    (Operation
    0.06
    .UltraWin
    0.06
    Act Density 0.000%

    No Known Activations