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

    Neuronpedia

    INDEX
    Explanations

    references to legal or formal documentation

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

    document sections and communications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.55
    PYX
    -0.49
     convidados
    -0.47
     fakty
    -0.47
     ſta
    -0.47
     beliau
    -0.46
    tagHelperRunner
    -0.45
     anún
    -0.44
    ſelf
    -0.43
    aarrggbb
    -0.43
    POSITIVE LOGITS
     ویکی‌پدیا
    0.40
    centralwidget
    0.39
    rea
    0.37
    nser
    0.36
    Fle
    0.36
     hochzeit
    0.36
    rašymas
    0.36
    ersk
    0.35
    EMOS
    0.35
    mian
    0.35
    Act Density 0.054%

    No Known Activations