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

    Neuronpedia

    INDEX
    Explanations

    date formats and slashes typically used in documentation

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

    dates with slashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contemporáneo
    -0.55
     pouvoit
    -0.53
     världen
    -0.53
     camiset
    -0.52
     contemporánea
    -0.50
     satisfecho
    -0.50
     Lengkap
    -0.49
     henvis
    -0.49
     rallado
    -0.49
     lâmpada
    -0.49
    POSITIVE LOGITS
    expandindo
    0.63
     Sept
    0.59
     June
    0.59
     July
    0.59
     April
    0.57
     March
    0.57
    July
    0.57
    /
    0.57
     September
    0.56
     Jan
    0.56
    Act Density 0.005%

    No Known Activations