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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions or terms related to statistics and probability

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

    Numbers inside parentheses and bold font

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ="@+
    -0.61
     препратки
    -0.60
    ParallelGroup
    -0.58
     $[-
    -0.54
    írus
    -0.54
     $]$
    -0.53
    فایل‌لار
    -0.53
    ัพท์
    -0.52
    .$_
    -0.51
    __;
    -0.51
    POSITIVE LOGITS
    -
    0.73
    دانشنامهٔ
    0.69
    migrationBuilder
    0.58
    jsxFileName
    0.57
    â
    0.54
     ब्रेकडाउन
    0.54
    StoreMessageInfo
    0.53
    contentLoaded
    0.53
    qtype
    0.52
     fieldNum
    0.50
    Act Density 0.330%

    No Known Activations