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

    Neuronpedia

    INDEX
    Explanations

    scientific article references and citation formats

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

    arXiv preprints with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.56
    énario
    -0.55
    transQ
    -0.53
    aarrggbb
    -0.52
     kasarigan
    -0.50
    NOPQRST
    -0.49
    brtc
    -0.48
    itattu
    -0.48
    uitton
    -0.47
    zzleHttp
    -0.47
    POSITIVE LOGITS
    ksjoner
    0.39
     beginnetje
    0.39
     exemplaire
    0.35
     largement
    0.35
    arXiv
    0.34
     flavours
    0.33
    asjons
    0.33
    šinou
    0.32
    دانشنامهٔ
    0.32
     étoit
    0.32
    Act Density 0.002%

    No Known Activations