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

    Neuronpedia

    INDEX
    Explanations

    URLs or web links

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

    start of user message

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ByUser
    -0.38
     sentarse
    -0.36
    XtraBars
    -0.34
     moeda
    -0.34
     soñar
    -0.33
    事實
    -0.33
     Ferner
    -0.33
     valentín
    -0.33
     coucher
    -0.32
     stanovnika
    -0.32
    POSITIVE LOGITS
    section
    0.84
    ंदीखरीदारी
    0.68
    providedIn
    0.64
    subsubsection
    0.63
    RegressionTest
    0.62
    parsedMessage
    0.59
    subsection
    0.57
    MessageOf
    0.56
    <h1>
    0.55
    addCriterion
    0.54
    Act Density 0.000%

    No Known Activations