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

    Neuronpedia

    INDEX
    Explanations

    ± SD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    पत्र
    0.73
    t
    0.73
    _{
    0.71
    —
    0.70
     or
    0.66
     Volume
    0.65
     possible
    0.64
    गु
    0.63
     –
    0.63
    –
    0.63
    POSITIVE LOGITS
     complicaciones
    0.97
     hea
    0.91
     hablar
    0.91
     comenzaron
    0.90
     tenemos
    0.89
     epile
    0.87
     realizaron
    0.87
     expresar
    0.87
     obter
    0.86
     bero
    0.86
    Act Density 0.000%

    No Known Activations