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

    Neuronpedia

    INDEX
    Explanations

    technical terms and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irrahim
    0.58
     निपट
    0.54
    ätzung
    0.53
     യൂണി
    0.50
     который
    0.49
    स्तेमाल
    0.48
    apayati
    0.48
     መሳሪያ
    0.48
     어떤
    0.47
    Databaze
    0.47
    POSITIVE LOGITS
    SS
    0.40
    豪華
    0.38
    Só
    0.38
    っている
    0.37
    Caf
    0.37
    Ass
    0.37
     Grande
    0.37
    相同
    0.37
    ুব
    0.36
     tempData
    0.36
    Act Density 0.001%

    No Known Activations