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

    Neuronpedia

    INDEX
    Explanations

    hit by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictate
    -0.07
     Comput
    -0.06
     categor
    -0.06
     rainy
    -0.06
     getir
    -0.06
     kingdom
    -0.06
    numero
    -0.06
     cautiously
    -0.06
    OKIE
    -0.06
    opol
    -0.06
    POSITIVE LOGITS
     초기
    0.07
    ><?=$
    0.07
    .Localization
    0.07
    addWidget
    0.07
    .event
    0.07
     관리자
    0.06
    力
    0.06
    inion
    0.06
    オリ
    0.06
    .<
    0.06
    Act Density 0.018%

    No Known Activations