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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    自由に
    0.46
    archiw
    0.44
    ἰ
    0.44
    icrosoft
    0.43
    ttps
    0.43
    ப்பிக்க
    0.43
    "?:
    0.43
    зяржа
    0.42
    aphazard
    0.42
    anggilan
    0.42
    POSITIVE LOGITS
     regulations
    0.44
     specimens
    0.44
    ের
    0.43
     nên
    0.43
    는
    0.43
    ,
    0.43
     that
    0.42
     özelliği
    0.40
     di
    0.40
     with
    0.40
    Act Density 0.128%

    No Known Activations