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

    Neuronpedia

    INDEX
    Explanations

    key terms related to specifications, criteria, and conditions in formal documents

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

    following X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.60
    MessageTagHelper
    -0.57
     ModelExpression
    -0.57
    exitRule
    -0.56
    ImageContext
    -0.55
     Paglinawan
    -0.54
    BeginContext
    -0.53
    RenderAtEndOf
    -0.51
    pexpr
    -0.49
    تقاوى
    -0.49
    POSITIVE LOGITS
     following
    0.87
    following
    0.70
    Following
    0.70
     Following
    0.69
     suivants
    0.68
     suivante
    0.68
     berikut
    0.67
     FOLLOWING
    0.65
     følgende
    0.64
     suivantes
    0.63
    Act Density 0.039%

    No Known Activations