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

    Neuronpedia

    INDEX
    Explanations

    lists or topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fernando
    0.41
     età
    0.39
     feito
    0.38
     bilirubin
    0.38
     ronde
    0.38
    ูป
    0.38
     Dekker
    0.37
     totaal
    0.37
     bilinear
    0.37
     külön
    0.37
    POSITIVE LOGITS
    Jimmy
    0.64
     Jimmy
    0.59
    Acet
    0.54
     acet
    0.44
     Acet
    0.42
     Reasoning
    0.40
    Glo
    0.40
    ವರ್
    0.39
    Id
    0.37
    Na
    0.37
    Act Density 0.001%

    No Known Activations