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

    Neuronpedia

    INDEX
    Explanations

    days and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reiterate
    0.48
    يلي
    0.45
     probabil
    0.43
     bipartisan
    0.43
     likelihood
    0.43
    ంచ్
    0.43
     perceptive
    0.42
    कारात्मक
    0.42
     implicate
    0.41
    मीत
    0.40
    POSITIVE LOGITS
    4
    0.54
    0.52
    :
    0.51
     fyra
    0.50
     damals
    0.49
    .
    0.48
     wäre
    0.46
    ۔
    0.46
    ierung
    0.45
     scuola
    0.45
    Act Density 0.521%

    No Known Activations