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

    Neuronpedia

    INDEX
    Explanations

    programming and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ا
    1.14
    ה
    0.98
    bollah
    0.97
    ు
    0.95
    ₍
    0.94
     tentacles
    0.89
    ைக்கு
    0.88
    ioners
    0.87
    aság
    0.86
    靼
    0.84
    POSITIVE LOGITS
    д
    0.94
    ítása
    0.91
    Blueprint
    0.80
    hentication
    0.79
    c
    0.78
    achten
    0.75
    いう
    0.74
     Cũng
    0.73
     температура
    0.73
    les
    0.73
    Act Density 0.024%

    No Known Activations