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

    Neuronpedia

    INDEX
    Explanations

    specific measurements or quantities related to scientific experiments

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

    Values with "µ" or "nm" units

    np_acts-logits-general · gemini-2.0-flash

    units of measurement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelben
    -0.83
    parsedMessage
    -0.81
    RegressionTest
    -0.77
     zuſammen
    -0.74
     beſch
    -0.73
    iſen
    -0.73
     beſte
    -0.73
    往下閱讀
    -0.72
    writeFieldEnd
    -0.71
     שוליים
    -0.71
    POSITIVE LOGITS
     psic
    0.25
     pommes
    0.23
    Kapcsolódó
    0.23
    {~
    0.23
    argb
    0.23
     bébés
    0.23
     instead
    0.22
     caoutchouc
    0.22
     frische
    0.22
     météoro
    0.22
    Act Density 0.707%

    No Known Activations