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

    Neuronpedia

    INDEX
    Explanations

    semicolons used in programming code

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

    initializer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.37
    \{\\
    -0.37
     sichere
    -0.35
    Ծանոթ
    -0.35
    ślę
    -0.33
    GOTREF
    -0.33
    úrese
    -0.32
    ✷
    -0.32
     infierno
    -0.31
     sää
    -0.31
    POSITIVE LOGITS
    bkz
    0.54
    RTGC
    0.52
     nargin
    0.51
     Alfaro
    0.51
    onOptions
    0.50
    useState
    0.49
    dataloader
    0.49
     Benav
    0.49
    CTOR
    0.47
     okuyayım
    0.47
    Act Density 0.005%

    No Known Activations