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

    Neuronpedia

    INDEX
    Explanations

    considerations and nuances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.50
     EPS
    0.46
    "
    0.44
    orphous
    0.44
    တ်
    0.44
     lip
    0.43
     actualizar
    0.43
    !
    0.42
     odometer
    0.41
     pistons
    0.41
    POSITIVE LOGITS
    সম্পাদক
    0.50
    Ná
    0.48
    長さ
    0.46
    Manisha
    0.46
    przy
    0.45
    Dieser
    0.45
    Tiene
    0.45
     Tud
    0.44
    ド
    0.44
    빽
    0.44
    Act Density 0.002%

    No Known Activations