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

    Neuronpedia

    INDEX
    Explanations

    programming or coding constructs related to data structures and functions

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

    Characters related to code or math

    np_acts-logits-general · gemini-2.0-flash

    code symbols and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.57
     nahilalakip
    -0.56
     CURIAM
    -0.55
     المعيارى
    -0.54
     >=",
    -0.51
    SequentialGroup
    -0.50
    لينكات
    -0.50
    новниш
    -0.49
     GenerationType
    -0.49
     Undeclared
    -0.49
    POSITIVE LOGITS
    duur
    0.31
    här
    0.30
     BoxFit
    0.29
    elli
    0.29
    JNIEnv
    0.28
     Rober
    0.28
    缓缓
    0.28
    ifan
    0.28
    um
    0.27
    ッケ
    0.27
    Act Density 0.234%

    No Known Activations