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

    Neuronpedia

    INDEX
    Explanations

    code declarations and structure in programming terminology

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

    C++ headers and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.77
     kaarangay
    -0.76
    expandindo
    -0.68
     MainAxisSize
    -0.64
    JNIEnv
    -0.61
     onAnimation
    -0.60
    ModelAdmin
    -0.59
    ollectionView
    -0.59
     مشين
    -0.58
    wpi
    -0.57
    POSITIVE LOGITS
    dotenv
    1.68
     dotenv
    0.77
     poko
    0.34
     environmental
    0.33
    fillna
    0.30
    oneph
    0.28
    łość
    0.28
    ément
    0.28
     influência
    0.27
     ENVIRONMENTAL
    0.27
    Act Density 0.001%

    No Known Activations