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

    Neuronpedia

    INDEX
    Explanations

    DO NOT

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    РА
    0.71
    Inicio
    0.70
    cantidad
    0.70
    mensaje
    0.70
    Cantidad
    0.68
    Buscar
    0.68
    CLOSE
    0.68
     DENUMIRE
    0.67
    muestra
    0.65
     Mannschaften
    0.64
    POSITIVE LOGITS
     In
    0.80
     A
    0.74
     And
    0.69
     For
    0.66
     An
    0.66
     To
    0.65
     IT
    0.63
     Des
    0.63
     Pro
    0.63
     Re
    0.63
    Act Density 0.034%

    No Known Activations