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

    Neuronpedia

    INDEX
    Explanations

    parts of code or functions that involve calculations or data manipulations

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

    Numbers "four" or "fourth"

    np_acts-logits-general · gemini-2.0-flash

    four and fourth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.57
    بوابة
    -0.55
    amoja
    -0.49
     ages
    -0.47
    dike
    -0.46
    
    -0.46
    enumii
    -0.45
    2
    -0.45
     désolés
    -0.45
    setLayoutManager
    -0.44
    POSITIVE LOGITS
     keempat
    0.62
     Fourteenth
    0.61
     fourth
    0.60
    ⁴
    0.60
    upar
    0.58
     four
    0.58
     fourteenth
    0.58
     Forty
    0.55
     विश्वसनीयता
    0.55
     quattro
    0.54
    Act Density 0.073%

    No Known Activations