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

    Neuronpedia

    INDEX
    Explanations

    generate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Même
    0.89
     Mesmo
    0.83
     agregar
    0.82
     Hasta
    0.82
     incluir
    0.80
     alcance
    0.78
     prenez
    0.77
     empieza
    0.77
     analizar
    0.76
     olsun
    0.76
    POSITIVE LOGITS
    ding
    0.77
    ็ง
    0.71
    up
    0.70
    cing
    0.70
    ствия
    0.70
    alling
    0.70
    nts
    0.69
    ng
    0.68
    css
    0.68
    cial
    0.67
    Act Density 0.002%

    No Known Activations