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

    Neuronpedia

    INDEX
    Explanations

    the presence of end-of-turn markers in text

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

    scientific and technical text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.69
    styleType
    -0.53
     للمعارف
    -0.53
     FetchType
    -0.52
    sprozess
    -0.51
    annica
    -0.49
    keyColumn
    -0.48
     palsu
    -0.48
     transfieras
    -0.47
    gimento
    -0.47
    POSITIVE LOGITS
    awaiter
    0.46
     *
    0.34
     seme
    0.33
    --]
    0.32
    ")));
    0.31
    ]");
    0.30
     linkovi
    0.30
    Hmmm
    0.30
    TagMode
    0.30
    KTM
    0.30
    Act Density 0.272%

    No Known Activations