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

    Neuronpedia

    INDEX
    Explanations

    car or severe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    აც
    0.81
    Votre
    0.80
    Selecion
    0.79
    ❢
    0.78
    મ
    0.76
    ு
    0.73
     участие
    0.72
     potentiel
    0.72
    ди
    0.71
     droit
    0.70
    POSITIVE LOGITS
    wikidata
    0.82
     ReLU
    0.81
     Przed
    0.79
     wę
    0.79
     Nordstrom
    0.78
     kterou
    0.76
     Takashi
    0.76
     Yuki
    0.76
    ার্স
    0.75
     Collar
    0.74
    Act Density 0.000%

    No Known Activations