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

    Neuronpedia

    INDEX
    Explanations

    sp or spr prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     સ્વ
    0.98
     visto
    0.95
     sama
    0.94
    丧
    0.94
    пия
    0.93
     sala
    0.92
     scrambling
    0.91
     свое
    0.87
     сма
    0.86
    ני
    0.84
    POSITIVE LOGITS
     SP
    1.31
     СП
    1.12
     Sp
    1.06
    inoza
    1.05
    ulative
    1.04
    ರ್ಧ
    1.03
    Sp
    1.00
    irtual
    0.99
    ัญลักษณ์
    0.98
     UIStoryboard
    0.98
    Act Density 0.498%

    No Known Activations