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

    Neuronpedia

    INDEX
    Explanations

    local context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     national
    0.79
     nacionais
    0.78
     nasional
    0.76
     interrupted
    0.72
    national
    0.72
    local
    0.70
     Nasional
    0.69
     nationale
    0.68
    iac
    0.67
    Ď
    0.66
    POSITIVE LOGITS
    izados
    0.98
    vore
    0.93
    izaciones
    0.89
    izadas
    0.87
    ized
    0.86
     पातळी
    0.85
    ise
    0.85
     голова
    0.83
    bit
    0.81
    য়নের
    0.80
    Act Density 0.158%

    No Known Activations