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

    Neuronpedia

    INDEX
    Explanations

    facts and objective information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confused
    -0.06
     MB
    -0.06
    loit
    -0.06
    :str
    -0.06
    och
    -0.06
    ично
    -0.06
    .Network
    -0.06
     TLabel
    -0.06
     Роз
    -0.06
     Patch
    -0.06
    POSITIVE LOGITS
     그가
    0.06
    strtotime
    0.06
     seasons
    0.06
     tendencies
    0.06
     admission
    0.06
    Unless
    0.06
     الأمريكية
    0.06
     relics
    0.06
    文章
    0.06
     judge
    0.06
    Act Density 0.001%

    No Known Activations