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

    Neuronpedia

    INDEX
    Explanations

    instances of programming syntax or structure

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

    basic math comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.55
    MLLoader
    -0.54
     navideño
    -0.49
    liceerd
    -0.49
     láser
    -0.47
     Autorisations
    -0.47
     BoxFit
    -0.47
    новниш
    -0.46
     navideña
    -0.45
     صوتيه
    -0.44
    POSITIVE LOGITS
     fundamentals
    0.45
     basic
    0.44
     meta
    0.42
     fundamental
    0.41
     Fundamentals
    0.39
    Искәрмәләр
    0.39
     Basic
    0.38
     ret
    0.38
     metast
    0.38
     fre
    0.36
    Act Density 0.025%

    No Known Activations