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

    Neuronpedia

    INDEX
    Explanations

    R/RA/Raw/Rap/Russian

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hydrox
    0.97
    ड़की
    0.94
     vire
    0.87
    haviour
    0.85
     座
    0.85
    cribing
    0.84
    ohol
    0.83
     toric
    0.81
     불구하고
    0.81
     vaga
    0.81
    POSITIVE LOGITS
     всего
    0.96
     cuadrada
    0.95
    お
    0.87
    ።
    0.86
     основы
    0.84
     умно
    0.83
    有
    0.83
     uncooked
    0.82
     founding
    0.82
     quadrada
    0.82
    Act Density 0.191%

    No Known Activations