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

    Neuronpedia

    INDEX
    Explanations

    lists or bullet points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     singleRun
    0.46
    виль
    0.44
     réalise
    0.44
    ները
    0.44
    0.41
    榖
    0.41
    ణి
    0.41
     pełni
    0.41
    преде
    0.40
     snippetHide
    0.40
    POSITIVE LOGITS
    :
    0.50
    İ
    0.49
    row
    0.47
    am
    0.45
    al
    0.43
    ：
    0.41
     İ
    0.41
    el
    0.40
     OV
    0.40
    info
    0.40
    Act Density 0.026%

    No Known Activations