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

    Neuronpedia

    INDEX
    Explanations

    specific JSON syntax elements, such as keys, values, and structural annotations

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

    JSON structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.44
    .
    -0.36
     La
    -0.35
     Ha
    -0.33
    …
    -0.33
     combine
    -0.33
     My
    -0.33
     Lac
    -0.33
     None
    -0.31
     Bes
    -0.31
    POSITIVE LOGITS
    transQ
    0.84
     kasarigan
    0.76
     snippetHide
    0.74
    ьаж
    0.67
     חיצוניים
    0.64
    contentLoaded
    0.63
     EconPapers
    0.63
     HasFactory
    0.63
    iſchen
    0.61
     zwey
    0.61
    Act Density 0.091%

    No Known Activations