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

    Neuronpedia

    INDEX
    Explanations

    phrase or clause continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ants
    0.41
     жало
    0.39
    explored
    0.38
    iciary
    0.38
     병
    0.38
    惋
    0.37
     గు
    0.37
    auz
    0.37
    병
    0.36
    rant
    0.36
    POSITIVE LOGITS
    Model
    0.42
     modèle
    0.42
     modello
    0.42
     modelo
    0.39
    بسم
    0.38
    Muhammad
    0.37
    型
    0.37
    誕生日
    0.37
    lova
    0.36
    ሞች
    0.36
    Act Density 0.000%

    No Known Activations