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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a new text or paragraph

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

    Preceding initials or short words

    np_acts-logits-general · gemini-2.0-flash

    supported by or personal representatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     /\.(
    -0.57
    tuta
    -0.54
    KEYCODE
    -0.54
    Билгалдахарш
    -0.54
    MessageState
    -0.53
    abestanden
    -0.53
    例句
    -0.53
    Portály
    -0.52
     виправивши
    -0.52
    +#+#
    -0.51
    POSITIVE LOGITS
    tamment
    0.54
    bietern
    0.52
    thritis
    0.51
     pály
    0.51
     tilbud
    0.50
     mourut
    0.50
     polypropylene
    0.50
    vidla
    0.49
    gway
    0.49
     canadien
    0.48
    Act Density 0.039%

    No Known Activations