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

    Neuronpedia

    INDEX
    Explanations

    ellipses or incomplete thoughts

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

    Text after ellipses/omissions

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by units like km

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     LUMP
    -0.63
    ietic
    -0.61
     defaultstate
    -0.59
    TagHelper
    -0.56
     Stur
    -0.55
    ;*/
    -0.55
    tometer
    -0.53
    parsedMessage
    -0.53
    клопе
    -0.53
    ErrorListener
    -0.52
    POSITIVE LOGITS
    /…
    0.96
    .…
    0.80
    …,
    0.77
    ,…
    0.74
    …’
    0.74
    "…
    0.73
    ”…
    0.73
     …
    0.73
     “…
    0.72
    addContainerGap
    0.71
    Act Density 0.340%

    No Known Activations