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

    Neuronpedia

    INDEX
    Explanations

    words related to religion and violence

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    يكب
    -0.53
     scolaires
    -0.51
     froide
    -0.48
     tilf
    -0.48
    lippery
    -0.47
     démocr
    -0.47
     Италијани
    -0.47
     scolaire
    -0.46
     llev
    -0.45
     piedi
    -0.45
    POSITIVE LOGITS
    IntoConstraints
    0.69
    脚注の使い方
    0.66
    rungsseite
    0.66
     MotionEvent
    0.65
    دانشنامهٔ
    0.60
    LLocation
    0.59
     StringTokenizer
    0.59
    !*\
    0.59
    TargetException
    0.59
     CreateTagHelper
    0.57
    Act Density 0.472%

    No Known Activations