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

    Neuronpedia

    INDEX
    Explanations

    SQL SUBSTRING and related functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۰
    1.38
    I
    1.34
    У
    1.32
    ли
    1.28
     μία
    1.27
    O
    1.25
    ר
    1.24
     willfully
    1.20
    𝟬
    1.18
     semblables
    1.12
    POSITIVE LOGITS
    as
    1.33
    k
    1.28
    m
    1.20
     i
    1.16
    is
    1.13
    ים
    1.08
    า
    1.07
    </h3>
    1.05
    tan
    0.99
    ta
    0.97
    Act Density 0.000%

    No Known Activations