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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols used in formulas

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

    Mathematical symbols or expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical symbols like lambda beta mu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    first
    -0.42
    …
    -0.42
     alma
    -0.41
    —
    -0.41
    Wednesday
    -0.41
    ***
    -0.40
    E
    -0.39
    First
    -0.39
    ..
    -0.39
    .
    -0.39
    POSITIVE LOGITS
    RUnlock
    0.87
    OGND
    0.85
     AttributeSet
    0.82
     المعيارى
    0.80
    StructEnd
    0.79
    RTEX
    0.79
    MIDDLEWARE
    0.78
     صوتيه
    0.76
     tartalomajánló
    0.74
     оригіналу
    0.74
    Act Density 0.665%

    No Known Activations