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

    Neuronpedia

    INDEX
    Explanations

    code structure delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    del
    0.40
    na
    0.39
     composer
    0.39
    _{\
    0.38
    UE
    0.38
    hu
    0.38
    str
    0.36
    arah
    0.36
     del
    0.36
     seeded
    0.36
    POSITIVE LOGITS
    𝓶
    0.46
     ܐ
    0.44
    냉
    0.43
    Katie
    0.43
     kalam
    0.43
    ष्ण
    0.42
     Cál
    0.42
     いっ
    0.42
     otras
    0.41
     Evaluations
    0.41
    Act Density 0.001%

    No Known Activations