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

    Neuronpedia

    INDEX
    Explanations

    Spanish gerunds and verb endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aches
    0.65
     itulah
    0.65
     behold
    0.61
     THAT
    0.60
    fare
    0.60
     evidente
    0.57
     that
    0.57
     একটা
    0.56
     es
    0.56
     upoz
    0.53
    POSITIVE LOGITS
     ngok
    0.81
     arbitrarily
    0.80
     Dynamical
    0.78
     fraudulently
    0.77
     নিরাপ
    0.75
     secretly
    0.75
     manualmente
    0.74
     सख्ती
    0.74
     regularmente
    0.74
     vertical
    0.74
    Act Density 0.107%

    No Known Activations