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

    Neuronpedia

    INDEX
    Explanations

    abstract class and method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thiệu
    1.39
    ٧
    1.30
     thích
    1.29
     adjectives
    1.26
     množství
    1.23
    irao
    1.21
     $\|\
    1.20
    钏
    1.20
     Rfc
    1.20
    ❤❤
    1.19
    POSITIVE LOGITS
    move
    1.53
    p
    1.35
    rete
    1.30
    numer
    1.21
    où
    1.19
    یه
    1.16
    dbo
    1.14
    came
    1.14
    got
    1.14
    altra
    1.13
    Act Density 0.000%

    No Known Activations