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

    Neuronpedia

    INDEX
    Explanations

    шо ты? Яндекс

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    YNAMICS
    0.50
    ⊡
    0.49
     phenotypic
    0.48
     elementos
    0.47
     lediglich
    0.47
    كلات
    0.47
    STRAINT
    0.46
     కారణంగా
    0.46
    performing
    0.45
    ﺍ
    0.45
    POSITIVE LOGITS
     есть
    0.73
    )))
    0.66
     нужен
    0.65
     вот
    0.63
     тут
    0.63
     как
    0.59
     мы
    0.58
     Есть
    0.58
     больше
    0.58
    есть
    0.58
    Act Density 0.042%

    No Known Activations