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

    Neuronpedia

    INDEX
    Explanations

    created by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slic
    0.43
    spr
    0.40
    suits
    0.39
    ﺋ
    0.39
     Gin
    0.38
    Spr
    0.37
    terr
    0.37
     Nak
    0.35
     سر
    0.35
     Spr
    0.35
    POSITIVE LOGITS
     ((*
    0.39
    郸
    0.37
    atemala
    0.36
    ন্ত্রী
    0.36
    āra
    0.36
    🍡
    0.35
     विष्णु
    0.35
     rebates
    0.35
     remboursement
    0.34
    GTA
    0.34
    Act Density 0.009%

    No Known Activations