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

    Neuronpedia

    INDEX
    Explanations

    heard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (gs
    -0.07
     collaborations
    -0.07
     Aless
    -0.07
     lash
    -0.07
    isten
    -0.06
    Appear
    -0.06
    (ExpectedConditions
    -0.06
    pants
    -0.06
    müş
    -0.06
    iş
    -0.06
    POSITIVE LOGITS
    라도
    0.06
    Dst
    0.06
    _agg
    0.06
     yapıldı
    0.06
     untrue
    0.06
     λέ
    0.06
     heard
    0.05
     Ware
    0.05
    IA
    0.05
     Knock
    0.05
    Act Density 0.015%

    No Known Activations