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

    Neuronpedia

    INDEX
    Explanations

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ی
    1.18
    γ
    1.02
    Efter
    0.87
    Uttar
    0.86
    法
    0.82
    跛
    0.80
    a
    0.80
    I
    0.79
    Ecco
    0.76
    Planck
    0.76
    POSITIVE LOGITS
    ні
    1.41
    asmuch
    1.23
    ुल्लाह
    1.23
     spacers
    1.20
    ти
    1.16
     steril
    1.13
     लीजिएगा
    1.12
    ों
    1.10
    ের
    1.09
     instalación
    1.09
    Act Density 0.000%

    No Known Activations