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

    Neuronpedia

    INDEX
    Explanations

    references to clues or mysteries that need to be solved

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    clues and secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bl
    -0.30
     non
    -0.29
    uxxxx
    -0.29
     miss
    -0.28
     Sine
    -0.28
     للمعارف
    -0.28
     classes
    -0.27
     [*]
    -0.27
     pareil
    -0.27
     Bo
    -0.27
    POSITIVE LOGITS
     rahasia
    0.66
     mystère
    0.63
     secrets
    0.63
    лтемелер
    0.63
     clues
    0.60
     secretos
    0.59
    LayoutStyle
    0.57
    secrets
    0.57
     henvisninger
    0.57
     mystery
    0.56
    Act Density 0.070%

    No Known Activations