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

    Neuronpedia

    INDEX
    Explanations

    sentences or sections with potentially incomplete or fragmented thoughts

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

    Ellipsis between words or numbers

    np_acts-logits-general · gemini-2.0-flash

    ellipsis and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NUKAT
    -0.68
    ỡng
    -0.68
    encodeWith
    -0.64
    =$?
    -0.62
    Bioaccumulative
    -0.61
    OGND
    -0.61
     MERCHANTABILITY
    -0.58
    ]_{\
    -0.57
    NUMX
    -0.57
    }?>
    -0.57
    POSITIVE LOGITS
     .
    0.79
     المعيارى
    0.70
    ValueStyle
    0.69
     виправивши
    0.65
     跳转至
    0.62
     .,
    0.54
     Horatio
    0.53
     дописавши
    0.53
    _.
    0.52
     kasarigan
    0.51
    Act Density 0.100%

    No Known Activations