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

    Neuronpedia

    INDEX
    Explanations

    Spanish nouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %
    0.57
    on
    0.51
     {}
    0.50
    isu
    0.50
    ro
    0.46
    asu
    0.45
    1
    0.45
    at
    0.45
    %
    0.44
    few
    0.44
    POSITIVE LOGITS
     Bridges
    0.66
     departamentos
    0.65
     steaks
    0.65
     Villa
    0.65
     baterías
    0.65
     aviones
    0.64
     botones
    0.63
     Tigers
    0.62
     sillas
    0.62
     planes
    0.62
    Act Density 0.000%

    No Known Activations