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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating frequency and repetition in narrative contexts

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

    basically describing states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spesies
    -0.33
     dokonce
    -0.33
    ここでは
    -0.32
     تكبرها
    -0.31
     whose
    -0.31
     đây
    -0.31
     plomb
    -0.31
    こちらは
    -0.30
    ailleurs
    -0.29
    NewUrlParser
    -0.29
    POSITIVE LOGITS
    :✨
    0.79
     pure
    0.70
     allemaal
    0.60
     all
    0.57
     just
    0.54
    pure
    0.53
    ɵɵelementEnd
    0.52
    就是
    0.52
     createSprite
    0.51
     PURE
    0.50
    Act Density 0.050%

    No Known Activations