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

    Neuronpedia

    INDEX
    Explanations

    error messages or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     after
    0.61
    ালে
    0.59
    సె
    0.58
     após
    0.56
     inspection
    0.56
     "."
    0.56
     if
    0.55
    CN
    0.55
    спи
    0.55
     nele
    0.55
    POSITIVE LOGITS
     மாற
    0.81
     Than
    0.74
    真正的
    0.73
    室
    0.70
    酒店
    0.70
     prawdzi
    0.69
    borhood
    0.69
     Scienze
    0.69
    шеб
    0.69
     Situ
    0.68
    Act Density 0.117%

    No Known Activations