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

    Neuronpedia

    INDEX
    Explanations

    Spanish 'to be' for description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jotka
    0.49
     главных
    0.48
     რომლებიც
    0.48
     которые
    0.48
     असलेले
    0.48
     jsou
    0.47
     असलेला
    0.47
     niektó
    0.46
    женные
    0.45
     janë
    0.45
    POSITIVE LOGITS
     capaz
    0.83
     bastante
    0.72
     susceptible
    0.67
     considerado
    0.67
     parte
    0.65
     capable
    0.62
     altamente
    0.61
     increíble
    0.61
     motivo
    0.61
     necesario
    0.60
    Act Density 0.035%

    No Known Activations