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

    Neuronpedia

    INDEX
    Explanations

    operators in code discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    1.33
     f
    1.26
    不是
    1.16
     t
    1.11
    ang
    1.09
    定的
    1.09
     clin
    1.08
    どう
    1.07
    品的
    1.06
    ারে
    1.05
    POSITIVE LOGITS
    dollars
    1.34
    нің
    1.27
    diamine
    1.26
     Algebras
    1.25
    bedrooms
    1.25
    Baş
    1.24
    zv
    1.23
    ㈡
    1.23
    renergic
    1.22
    costs
    1.22
    Act Density 0.034%

    No Known Activations