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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ନ୍ତ
    0.46
     slabs
    0.42
     dT
    0.41
    elah
    0.39
     dallo
    0.39
     fronte
    0.38
    льному
    0.38
     মনোবল
    0.37
     )।
    0.37
     जनरल
    0.36
    POSITIVE LOGITS
    IR
    0.48
    FEL
    0.47
    IS
    0.45
    ificare
    0.42
    یس
    0.40
    isie
    0.39
    is
    0.39
     इजा
    0.39
    Lie
    0.38
     خلي
    0.38
    Act Density 0.000%

    No Known Activations