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

    Neuronpedia

    INDEX
    Explanations

    references to searching, observing, or investigating various topics

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

    look into or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.46
     ویکی‌پدیای
    -0.45
     değil
    -0.41
    locke
    -0.41
     שוליים
    -0.40
     للمعارف
    -0.40
    windowFixed
    -0.39
    ungsbedingungen
    -0.38
    gemä
    -0.38
    請繼續往下閱讀
    -0.38
    POSITIVE LOGITS
    MLLoader
    0.57
     defaultstate
    0.49
    BarItem
    0.45
    Cyfarwyddwr
    0.42
    nastics
    0.41
    PyErr
    0.41
     fis
    0.40
    pushFollow
    0.40
     browse
    0.40
     famili
    0.39
    Act Density 0.019%

    No Known Activations