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

    Neuronpedia

    INDEX
    Explanations

    drive-by downloads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.47
    ス
    0.41
     chale
    0.40
    ک
    0.40
    仕事
    0.40
    اک
    0.39
     peacock
    0.39
     impuls
    0.39
    di
    0.39
     sm
    0.38
    POSITIVE LOGITS
     返回
    0.60
     这里
    0.52
     请求
    0.50
    에게
    0.48
    ционер
    0.47
    返回
    0.46
    ListBox
    0.45
     요청
    0.45
     reservar
    0.44
     两
    0.44
    Act Density 0.004%

    No Known Activations