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

    Neuronpedia

    INDEX
    Explanations

    bulls not enraged by red

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abhuto
    0.46
     YOUR
    0.46
     केल्यानंतर
    0.42
     것입니다
    0.42
    羮
    0.42
    ใช่
    0.41
    擴
    0.41
    ูนย์
    0.41
     {}>
    0.40
     বাহিনীর
    0.40
    POSITIVE LOGITS
    roph
    0.44
     neues
    0.43
     vermutlich
    0.41
    atore
    0.41
    qk
    0.40
     mencionados
    0.40
     ذكر
    0.39
     Bela
    0.39
     entier
    0.39
     seem
    0.39
    Act Density 0.004%

    No Known Activations