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

    Neuronpedia

    INDEX
    Explanations

    rules of, specifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ováno
    1.14
    에게
    1.02
     oplossing
    0.97
     kuris
    0.96
    contains
    0.95
     яке
    0.92
    സിന്
    0.87
    terminus
    0.84
    two
    0.83
     విధంగా
    0.83
    POSITIVE LOGITS
     galore
    1.67
     related
    1.53
     outlined
    1.47
     relating
    1.43
     gleaned
    1.39
     pertaining
    1.35
     arising
    1.35
    pecific
    1.34
    heets
    1.33
     abound
    1.33
    Act Density 2.752%

    No Known Activations