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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas and expressions

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

    mathematical expressions with fractions and greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.69
    ########.
    -0.67
    Билгалдахарш
    -0.64
    期刊论文
    -0.61
    )];
    -0.55
    glBegin
    -0.54
     betweenstory
    -0.54
    styleType
    -0.54
    addContainerGap
    -0.53
    fillType
    -0.51
    POSITIVE LOGITS
     Италијани
    0.38
     Moscú
    0.36
     acá
    0.36
     Kerja
    0.35
     INTERESAR
    0.35
     terdekat
    0.35
    StructEnd
    0.35
     Roumanie
    0.34
     matière
    0.33
     ganancias
    0.32
    Act Density 0.243%

    No Known Activations