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

    Neuronpedia

    INDEX
    Explanations

    expressions of awareness or understanding

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

    Follows "know" or introduces questions

    np_acts-logits-general · gemini-2.0-flash

    you know what

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.86
    SourceChecksum
    -0.78
     صوتيه
    -0.76
    afficheront
    -0.73
     CreateTagHelper
    -0.68
    évaluateur
    -0.66
     Italijani
    -0.65
    ValueStyle
    -0.65
     Roskov
    -0.65
     invokingState
    -0.64
    POSITIVE LOGITS
     those
    0.62
     &___
    0.50
     when
    0.49
     what
    0.49
     why
    0.48
    használ
    0.47
     When
    0.47
    Those
    0.46
    Архівовано
    0.45
     Those
    0.45
    Act Density 0.030%

    No Known Activations