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

    Neuronpedia

    INDEX
    Explanations

    references to programming languages or technical concepts

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

    Numbers within file paths or code

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.02
    tagHelperRunner
    -0.82
    bootstrapcdn
    -0.75
    <unused14>
    -0.74
    <unused79>
    -0.74
    <unused74>
    -0.74
    <unused16>
    -0.74
    <unused8>
    -0.73
    <unused3>
    -0.73
    [@BOS@]
    -0.73
    POSITIVE LOGITS
    <eos>
    0.47
    -------------</
    0.38
     cuchar
    0.37
     kanya
    0.34
     pendientes
    0.33
     Farrell
    0.33
     prosím
    0.32
    Anmerkungen
    0.32
     Wolken
    0.31
     frühen
    0.31
    Act Density 0.016%

    No Known Activations