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

    Neuronpedia

    INDEX
    Explanations

    steer loaders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.88
    ()%
    0.84
     ẞ
    0.82
    +\
    0.80
    ভূতির
    0.79
    ys
    0.79
    istosoma
    0.78
    venues
    0.78
    erà
    0.78
    0.77
    POSITIVE LOGITS
    ം
    1.56
     lysate
    0.99
     воздух
    0.97
     limpia
    0.96
     recorrido
    0.96
     изучение
    0.96
     Verstappen
    0.93
     Fractals
    0.93
     Kamera
    0.93
     Thieves
    0.92
    Act Density 0.000%

    No Known Activations