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

    Neuronpedia

    INDEX
    Explanations

    words related to processes of modification or repetition

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

    actions starting with re

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []:
    -0.56
    Clik
    -0.55
    thums
    -0.52
    Slf
    -0.51
    ✭✭
    -0.50
    multer
    -0.49
    字
    -0.48
    — 
    -0.48
    astéroïdes
    -0.47
    算
    -0.47
    POSITIVE LOGITS
     reconnect
    0.68
     reopened
    0.66
     redesigned
    0.63
     ponownie
    0.61
    BibitemShut
    0.60
     reappeared
    0.60
     opnieuw
    0.60
     rejoin
    0.59
     reappear
    0.58
     yeniden
    0.58
    Act Density 0.039%

    No Known Activations