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

    Neuronpedia

    INDEX
    Explanations

    extract, redact, trim, scanning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gação
    0.42
     entendimento
    0.42
    PARTY
    0.41
    ائب
    0.41
     trabajado
    0.40
     asistente
    0.40
    ណ៌
    0.40
     intimidating
    0.39
     presentaciones
    0.39
    工地
    0.39
    POSITIVE LOGITS
     Jun
    0.46
     plas
    0.44
     Be
    0.41
    nos
    0.39
     A
    0.39
    \"
    0.38
     Kind
    0.38
    :
    0.38
     div
    0.38
     రా
    0.38
    Act Density 0.002%

    No Known Activations