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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사항
    1.17
    사항
    1.15
     coriander
    1.12
     revest
    1.08
     Jodi
    1.07
     lordship
    1.07
     RequestMethod
    1.07
    дентификаторы
    1.07
     slideshow
    1.07
     shear
    1.06
    POSITIVE LOGITS
    ت
    1.07
    enek
    1.02
    将
    1.02
    你
    1.01
    没有
    1.01
     nécessité
    0.98
    G
    0.95
    P
    0.94
    ﺕ
    0.93
    a
    0.92
    Act Density 0.006%

    No Known Activations