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

    Neuronpedia

    INDEX
    Explanations

    quantitative data or numeric values in a text

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

    Numbers found within sentences

    np_acts-logits-general · gemini-2.0-flash

    numbers following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kör
    -0.55
    userdetails
    -0.54
    moire
    -0.54
     estri
    -0.52
     setae
    -0.52
    findpost
    -0.51
     Abp
    -0.49
     שוליים
    -0.48
     concor
    -0.48
    øre
    -0.48
    POSITIVE LOGITS
    ThroughAttribute
    0.75
     dAtA
    0.70
    ClientSize
    0.68
    audiovisuel
    0.63
    __":
    0.62
     EconPapers
    0.61
    hão
    0.58
    antd
    0.58
    rxjs
    0.57
     BoxFit
    0.57
    Act Density 0.491%

    No Known Activations