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

    Neuronpedia

    INDEX
    Explanations

    code-related syntax and import statements

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

    "from" followed by a module or library name

    np_acts-logits-general · gemini-2.0-flash

    python import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.60
    expandindo
    -0.55
    featureID
    -0.53
    AntiForgeryToken
    -0.53
    IntoConstraints
    -0.52
     setEmail
    -0.52
    ContentAlignment
    -0.52
    orship
    -0.52
     فريبيس
    -0.52
    Hochspringen
    -0.51
    POSITIVE LOGITS
     cauliflower
    0.58
     Osh
    0.56
     Kats
    0.55
     UW
    0.55
     Fino
    0.54
     TAMBIÉN
    0.53
    jä
    0.53
     cà
    0.53
    </thead>
    0.52
    őle
    0.52
    Act Density 0.037%

    No Known Activations