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

    Neuronpedia

    INDEX
    Explanations

    open weights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     የማይ
    0.43
    ouvrir
    0.40
     فتحه
    0.39
     membuka
    0.39
    ኘት
    0.38
    (()
    0.38
    ivism
    0.37
     открыть
    0.37
    opensource
    0.37
    撇
    0.37
    POSITIVE LOGITS
    model
    0.61
    Model
    0.59
     model
    0.59
     Model
    0.55
     Moz
    0.51
     Modell
    0.50
     modèle
    0.49
     модели
    0.49
    模型
    0.48
     MODEL
    0.47
    Act Density 0.020%

    No Known Activations