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

    Neuronpedia

    INDEX
    Explanations

    any specific ideas or questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meskipun
    2.21
     ση
    2.13
    İlk
    2.12
    Bis
    2.09
    centric
    2.03
    ي
    2.02
    אה
    2.02
    англ
    1.97
    Là
    1.97
    ๆ
    1.93
    POSITIVE LOGITS
    ارات
    2.04
    ancers
    1.98
    [
    1.96
    ć
    1.95
     obvious
    1.79
     lr
    1.77
    ombie
    1.73
     ederim
    1.72
    ţin
    1.72
    ğin
    1.71
    Act Density 0.036%

    No Known Activations