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

    Neuronpedia

    INDEX
    Explanations

    numeric values and mathematical expressions

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

    code delimiters and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.75
    OGND
    -0.57
    GraphicsUnit
    -0.54
    ImageContext
    -0.52
    Tembelea
    -0.50
    haikusbot
    -0.49
    BeginInit
    -0.48
    Chham
    -0.47
    tagext
    -0.46
    Geplaatst
    -0.46
    POSITIVE LOGITS
     juzgar
    0.39
     <>",
    0.38
     paisagem
    0.37
    Havolalar
    0.37
     typelib
    0.35
     répertoire
    0.35
    paravant
    0.35
     pasada
    0.35
     somehow
    0.34
    barui
    0.34
    Act Density 0.018%

    No Known Activations