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

    Neuronpedia

    INDEX
    Explanations

    topics for content creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    टेक
    0.41
     punch
    0.41
    agai
    0.40
     bulletins
    0.40
    frozen
    0.38
    ύ
    0.38
    arbeit
    0.38
    jail
    0.38
    配置
    0.38
     fixes
    0.37
    POSITIVE LOGITS
    丝毫
    0.45
     очки
    0.42
     avendo
    0.42
     faintly
    0.41
     Energia
    0.41
     entrop
    0.41
    innitus
    0.40
     عدم
    0.40
     বিরত
    0.40
     Ehrlich
    0.40
    Act Density 0.001%

    No Known Activations