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

    Neuronpedia

    INDEX
    Explanations

    birth rate or infinite values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oxidación
    0.47
     sodio
    0.45
     saddhim
    0.42
    য্
    0.42
    橼
    0.41
    ానం
    0.41
    ھیں
    0.40
     വിൽപ്പന
    0.40
     ابراہیم
    0.40
    ట్స్‌మన్
    0.40
    POSITIVE LOGITS
    ↵
    0.58
    1
    0.52
     and
    0.50
    0
    0.50
     t
    0.49
    t
    0.49
    A
    0.49
    D
    0.48
    3
    0.48
     or
    0.46
    Act Density 0.000%

    No Known Activations