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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الب
    0.36
     والم
    0.33
    ཅ
    0.33
     audacity
    0.32
    ؟
    0.32
     longues
    0.32
    ﻒ
    0.31
    譎
    0.30
     femme
    0.30
     تُ
    0.30
    POSITIVE LOGITS
    还有一个
    0.32
     altres
    0.32
    another
    0.32
    `
    0.31
    in
    0.30
    u
    0.30
    的其他
    0.29
     другом
    0.29
    udel
    0.29
    ini
    0.29
    Act Density 0.310%

    No Known Activations