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

    Neuronpedia

    INDEX
    Explanations

    nested array structures

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

    `user` or `module` after `<start_of_turn>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſever
    -0.67
     Anſ
    -0.64
     itſelf
    -0.63
    LEncoder
    -0.63
     Verſ
    -0.63
    leſs
    -0.62
     autorytatywna
    -0.62
     pleaſure
    -0.62
     ſta
    -0.61
    alakip
    -0.61
    POSITIVE LOGITS
    phosa
    0.35
     muualla
    0.34
    yyj
    0.32
    UrlResolution
    0.31
    enumi
    0.30
    BeginContext
    0.30
    代わりに
    0.30
     okuyayım
    0.29
     Chwiliwch
    0.28
    ItemBackground
    0.27
    Act Density 0.043%

    No Known Activations