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

    Neuronpedia

    INDEX
    Explanations

    who is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    گ
    0.45
    icar
    0.42
    Описание
    0.42
    od
    0.42
    an
    0.42
    ד
    0.41
    ס
    0.41
    ân
    0.41
     inglés
    0.41
    使用
    0.40
    POSITIVE LOGITS
     Ate
    0.47
    ächst
    0.43
     ом
    0.42
     arousal
    0.41
     be
    0.40
    luent
    0.40
     Opportunity
    0.40
     ощущение
    0.39
     bx
    0.38
     bhavanti
    0.38
    Act Density 0.001%

    No Known Activations