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

    Neuronpedia

    INDEX
    Explanations

    Russian 'дома' and 'плохо'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     showcased
    0.94
     garnered
    0.92
     found
    0.86
     termed
    0.83
     showcasing
    0.80
     bestowed
    0.80
     gathered
    0.80
     undertaken
    0.80
     accounted
    0.79
     made
    0.78
    POSITIVE LOGITS
     плохо
    0.82
     dientes
    0.73
     roja
    0.71
     caminar
    0.69
     pines
    0.68
    Finland
    0.67
     árboles
    0.67
    Kub
    0.67
     argumentos
    0.66
    бера
    0.66
    Act Density 0.001%

    No Known Activations