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

    Neuronpedia

    INDEX
    Explanations

    discarded or publicly known

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     истории
    0.48
    某个
    0.47
     страхо
    0.46
     страда
    0.46
    规范
    0.45
     конкре
    0.44
     граждан
    0.44
    舺
    0.43
     управления
    0.42
     текста
    0.42
    POSITIVE LOGITS
     I
    0.54
     secreted
    0.49
    زمانہ
    0.48
    wo
    0.48
    வதில்லை
    0.47
    不會
    0.46
    super
    0.45
     not
    0.44
     vasocon
    0.44
    できない
    0.44
    Act Density 0.009%

    No Known Activations