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

    Neuronpedia

    INDEX
    Explanations

    open weights model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     모델
    0.49
     modeli
    0.44
    モデル
    0.43
     models
    0.42
     modellen
    0.42
     модель
    0.42
    模型的
    0.42
     मॉडल
    0.41
     modelu
    0.41
    models
    0.41
    POSITIVE LOGITS
    पू
    0.38
     Barak
    0.38
    TEC
    0.38
     salles
    0.38
     vacancy
    0.37
     tủ
    0.36
    GEN
    0.35
     motorized
    0.34
     பா
    0.34
    இது
    0.34
    Act Density 0.003%

    No Known Activations