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

    Neuronpedia

    INDEX
    Explanations

    first-person and collective pronouns indicating involvement or presence in the document

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

    we present or introduce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.52
    RepeatedField
    -0.47
    rungsseite
    -0.42
    Хьажоргаш
    -0.42
    putBoolean
    -0.37
     Wau
    -0.36
     Notwithstanding
    -0.35
    Despite
    -0.35
     Despite
    -0.35
    adaptiveStyles
    -0.35
    POSITIVE LOGITS
    ########.
    0.55
     purpoſe
    0.54
     nahilalakip
    0.49
     ſeveral
    0.47
     Diſ
    0.47
     ſte
    0.47
     pleaſure
    0.46
    antası
    0.45
     drums
    0.45
     houſe
    0.45
    Act Density 0.077%

    No Known Activations