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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and code structure

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

    programming code and mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    altham
    -0.47
    Tikang
    -0.44
     Sto
    -0.42
    anical
    -0.42
     Ran
    -0.42
     Hi
    -0.40
    komme
    -0.40
     зали
    -0.40
     Hay
    -0.40
     Ry
    -0.39
    POSITIVE LOGITS
    ########.
    0.50
    MLLoader
    0.47
     protoimpl
    0.47
    :+:
    0.46
    fillType
    0.45
    JspWriter
    0.44
    CppMethod
    0.43
     utafitiHapana
    0.43
    ConstraintMaker
    0.42
    Життєпис
    0.42
    Act Density 0.024%

    No Known Activations