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

    Neuronpedia

    INDEX
    Explanations

    scientific measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人人
    -0.08
    PEnd
    -0.07
     علي
    -0.06
    -vers
    -0.06
    .enable
    -0.06
    RouterModule
    -0.06
    전자
    -0.06
     Singles
    -0.06
     tuyển
    -0.06
    џЭ
    -0.06
    POSITIVE LOGITS
     refuge
    0.07
    умов
    0.07
     özellik
    0.07
     Jab
    0.07
    bishop
    0.06
    cargo
    0.06
     shortened
    0.06
    venth
    0.06
     affirmation
    0.06
    >,↵
    0.06
    Act Density 0.084%

    No Known Activations