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

    Neuronpedia

    INDEX
    Explanations

    regardless of circumstances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obody
    -0.07
    sl
    -0.07
     підтрим
    -0.06
     silver
    -0.06
     Relations
    -0.06
     thumbnail
    -0.06
    .wp
    -0.06
     flowed
    -0.06
     hust
    -0.06
     sw
    -0.06
    POSITIVE LOGITS
     malé
    0.06
    će
    0.06
    终于
    0.06
    licos
    0.06
    ター
    0.06
    (TokenType
    0.06
    、この
    0.06
     Rodrigo
    0.06
    _action
    0.06
    Surv
    0.06
    Act Density 0.006%

    No Known Activations