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

    Neuronpedia

    INDEX
    Explanations

    Khan Academy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lookup
    0.31
     Figure
    0.29
    9
    0.29
    DE
    0.29
    ~\
    0.28
    neb
    0.28
     ORGAN
    0.28
    равни
    0.28
    hood
    0.28
    dep
    0.28
    POSITIVE LOGITS
    Idents
    0.32
    周末
    0.32
     apopt
    0.31
     ಎ
    0.31
    ियमित
    0.31
    ванне
    0.31
    Xpaths
    0.30
     Macon
    0.30
     बजरंग
    0.30
     באמצעות
    0.30
    Act Density 0.005%

    No Known Activations