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

    Neuronpedia

    INDEX
    Explanations

    quantitative references and statistical data in studies

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

    proportion of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CharStream
    -0.39
     Pitch
    -0.36
     Performance
    -0.34
     sacré
    -0.34
     infinito
    -0.34
    municipio
    -0.34
    👔
    -0.34
    rsa
    -0.34
     Residents
    -0.33
    junto
    -0.33
    POSITIVE LOGITS
     argint
    0.60
     nahilalakip
    0.56
     rarely
    0.50
     egent
    0.49
     wenigen
    0.49
    InjectAttribute
    0.47
    ettare
    0.47
     barely
    0.46
     كومونز
    0.46
     eigentliche
    0.46
    Act Density 0.074%

    No Known Activations