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

    Neuronpedia

    INDEX
    Explanations

    phases and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     characterizing
    0.51
    欧
    0.47
    άζ
    0.46
    亿
    0.45
    ட்டர்
    0.44
    椭
    0.44
    τυ
    0.44
     elliptical
    0.44
    ΕΣ
    0.43
     accumulating
    0.43
    POSITIVE LOGITS
    lehem
    0.50
    degener
    0.50
    streng
    0.48
    jalan
    0.47
     विज्ञान
    0.47
    आप
    0.46
    hombre
    0.46
     परीक्षा
    0.46
    hatiti
    0.46
     взаимо
    0.45
    Act Density 0.001%

    No Known Activations