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

    Neuronpedia

    INDEX
    Explanations

    references to complex technical concepts and programming instructions

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

    Email signatures or separators

    np_acts-logits-general · gemini-2.0-flash

    Sent:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.69
     autorytatywna
    -0.67
    KommentareTeilen
    -0.66
    MLLoader
    -0.65
    transQ
    -0.63
    AndEndTag
    -0.60
    .";
    -0.59
    `;
    -0.58
    enzie
    -0.56
    日閲覧
    -0.56
    POSITIVE LOGITS
     Sent
    0.78
    >
    0.76
     -----
    0.73
    --
    0.70
     --
    0.70
     >
    0.69
    -----
    0.66
    Sent
    0.65
    >>
    0.62
    ---
    0.60
    Act Density 0.566%

    No Known Activations