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

    Neuronpedia

    INDEX
    Explanations

    terms related to technical functionalities and processes in programming

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

    after bracketed references (e.g. \[basiclowerbound\])

    np_acts-logits-general · gemini-2.0-flash

    program files quickly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.71
     autorytatywna
    -0.71
    OGND
    -0.63
    पया
    -0.52
     AssemblyCulture
    -0.52
     nahilalakip
    -0.52
     čierna
    -0.51
     chi̍t
    -0.51
    NameInMap
    -0.50
    ьаж
    -0.50
    POSITIVE LOGITS
     utafitiHapana
    0.50
    ordion
    0.41
    Fly
    0.40
    Ay
    0.38
    Het
    0.38
    onedDateTime
    0.37
     peix
    0.36
    tagHelper
    0.36
     webshop
    0.36
    UnusedPrivate
    0.36
    Act Density 0.955%

    No Known Activations