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

    Neuronpedia

    INDEX
    Explanations

    state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     traged
    -0.08
    .picture
    -0.07
     paved
    -0.07
     tragedy
    -0.07
     candid
    -0.07
     town
    -0.07
     unob
    -0.07
     Blvd
    -0.07
     babes
    -0.06
     pictures
    -0.06
    POSITIVE LOGITS
     初始化
    0.09
     حوالے
    0.09
     цяпер
    0.08
    初始化
    0.08
    orrer
    0.08
     гим
    0.08
    ابقة
    0.08
     состояние
    0.08
     fãs
    0.08
     toestand
    0.08
    Act Density 0.001%

    No Known Activations