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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and contrasts between different entities or concepts

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

    between, opposed, compared, spite

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    istoitu
    -0.71
     CreateTagHelper
    -0.68
    bootstrapcdn
    -0.62
    ⤒
    -0.61
    LayoutStyle
    -0.59
    Predecesor
    -0.59
    afficheront
    -0.58
     AssemblyCulture
    -0.57
    趨
    -0.56
     simplifié
    -0.56
    POSITIVE LOGITS
    ,
    0.54
    Anyways
    0.49
     Anyways
    0.45
     (
    0.44
    ResumeLayout
    0.43
     I
    0.42
     thing
    0.42
     whole
    0.42
     Anderson
    0.41
    Somebody
    0.41
    Act Density 0.014%

    No Known Activations