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

    Neuronpedia

    INDEX
    Explanations

    provided, scenario, helps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sebab
    0.99
     pidió
    0.98
     haciendo
    0.98
     diseño
    0.96
     sigu
    0.96
     agrade
    0.96
     cuero
    0.94
    творе
    0.91
     siguió
    0.91
    ધી
    0.89
    POSITIVE LOGITS
    ת
    0.80
    s
    0.74
    kan
    0.68
     Persian
    0.66
    tra
    0.65
    yr
    0.64
     R
    0.62
    sw
    0.61
    Av
    0.61
     AM
    0.61
    Act Density 0.000%

    No Known Activations