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

    Neuronpedia

    INDEX
    Explanations

    expressions of recommendation and positive sentiment

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

    Positive feedback and appreciation

    np_acts-logits-general · gemini-2.0-flash

    highly recommend / satisfy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.84
    parsedMessage
    -0.83
     المعيارى
    -0.75
    ſammen
    -0.74
     ब्रेकडाउन
    -0.72
    Билгалдахарш
    -0.68
     ویکی‌پدی
    -0.68
    GEBURTSDATUM
    -0.65
    Autoritní
    -0.65
     CreateTagHelper
    -0.65
    POSITIVE LOGITS
     every
    0.36
     truly
    0.34
     beautiful
    0.34
     special
    0.33
     really
    0.33
    !
    0.33
     excellence
    0.32
     I
    0.32
     👏
    0.32
    ️
    0.31
    Act Density 0.053%

    No Known Activations