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

    Neuronpedia

    INDEX
    Explanations

    fraud alert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uez
    0.48
    jar
    0.46
    issa
    0.45
    ismas
    0.44
    こともある
    0.42
    적이
    0.42
    筥
    0.41
    uminous
    0.41
    the
    0.41
    olf
    0.40
    POSITIVE LOGITS
    اتي
    0.55
     ogen
    0.52
     opio
    0.52
     povos
    0.52
     فبراير
    0.51
     milhares
    0.51
    Received
    0.50
     Primeiro
    0.50
    ای
    0.50
     estoppel
    0.50
    Act Density 0.000%

    No Known Activations