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

    Neuronpedia

    INDEX
    Explanations

    mathematical formatting and structure, particularly involving arrays, equations, and symbolic representations

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

    LaTeX math environments

    np_acts-logits-general · gemini-2.0-flash

    aligned math environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BagLayout
    -0.69
    TemporalType
    -0.67
    AspNetCore
    -0.66
     invokingState
    -0.66
     createSprite
    -0.65
    postsleuth
    -0.63
    saraba
    -0.63
     "'");
    -0.63
    {{/
    -0.62
    )))));
    -0.62
    POSITIVE LOGITS
     MainAxisSize
    0.45
     ARY
    0.44
    oriasis
    0.43
     推荐
    0.43
     Reiner
    0.42
     acidente
    0.42
    rubin
    0.41
     snorkel
    0.41
     userSchema
    0.41
    conduct
    0.40
    Act Density 0.088%

    No Known Activations