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

    Neuronpedia

    INDEX
    Explanations

    family member or group

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yd
    1.30
     is
    1.24
    ld
    1.15
     Dr
    1.14
     one
    1.13
    ank
    1.11
     Dun
    1.11
    Dr
    1.10
     v
    1.10
    واء
    1.09
    POSITIVE LOGITS
     Blurred
    1.42
     embaixo
    1.41
     merasakan
    1.37
     comest
    1.35
     compone
    1.35
     hipot
    1.34
    Localized
    1.33
     voli
    1.32
     складі
    1.32
    цева
    1.28
    Act Density 0.436%

    No Known Activations