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

    Neuronpedia

    INDEX
    Explanations

    items related to visual elements and graphical representation

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

    spatial direction and borders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contr
    -0.36
    官
    -0.35
    MetaObject
    -0.32
     desierto
    -0.31
     vastaan
    -0.30
     tork
    -0.29
    localctx
    -0.28
    扫
    -0.28
     odd
    -0.27
     banged
    -0.26
    POSITIVE LOGITS
    MessageOf
    0.78
     autorytatywna
    0.77
     CanadaChoose
    0.74
    GEBURTSDATUM
    0.71
    Autoritní
    0.70
     виправивши
    0.69
     للمعارف
    0.67
    RenderAtEndOf
    0.66
    tagHelperRunner
    0.65
    extAlignment
    0.65
    Act Density 0.269%

    No Known Activations