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

    Neuronpedia

    INDEX
    Explanations

    wheels, rodas, roda

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    خة
    0.68
     Divisional
    0.66
     coworker
    0.64
    fence
    0.64
    дая
    0.63
     exemplaire
    0.62
    usal
    0.62
    REST
    0.62
    ump
    0.61
    Composer
    0.61
    POSITIVE LOGITS
     wheels
    0.90
     Wheels
    0.83
     এরই
    0.82
     rodas
    0.82
    ρό
    0.78
    തിന്റെ
    0.76
    roids
    0.76
     roda
    0.74
     Jakub
    0.74
    ுகளை
    0.73
    Act Density 0.001%

    No Known Activations