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

    Neuronpedia

    INDEX
    Explanations

    prepositions indicating relationships in time or space

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

    grows in or changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.66
     للاسماء
    -0.65
    awtextra
    -0.60
    uxxxx
    -0.60
    IsPostBack
    -0.57
     MotionEvent
    -0.54
    脚注の使い方
    -0.53
    colgroup
    -0.53
     '\\;'
    -0.52
    Hentet
    -0.51
    POSITIVE LOGITS
     mecánico
    0.52
     Keuangan
    0.49
     descub
    0.45
     húmedo
    0.44
     sambung
    0.43
     perfección
    0.43
     infierno
    0.42
     financiero
    0.42
     guste
    0.41
     flota
    0.40
    Act Density 0.138%

    No Known Activations