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

    Neuronpedia

    INDEX
    Explanations

    references to scientific literature and methodologies

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

    before commas or parentheses

    np_acts-logits-general · gemini-2.0-flash

    specific scientific concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lui
    -0.67
     mnie
    -0.58
    是她
    -0.58
    herself
    -0.55
     eux
    -0.55
    让她
    -0.54
    在我
    -0.53
    在她
    -0.52
    被他
    -0.52
     vuotta
    -0.52
    POSITIVE LOGITS
     there
    2.00
     it
    1.69
     they
    1.53
     we
    1.45
     the
    1.29
    there
    1.28
     everything
    1.23
     nothing
    1.20
     you
    1.14
     theres
    1.13
    Act Density 1.079%

    No Known Activations