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

    Neuronpedia

    INDEX
    Explanations

    helpful and harmless

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    highlight
    0.88
     thấy
    0.83
     highlight
    0.81
    enhanced
    0.80
    ibe
    0.79
     sound
    0.78
    sound
    0.75
    im
    0.75
     exercise
    0.75
    শ্বর
    0.74
    POSITIVE LOGITS
    desk
    0.93
     đỡ
    0.92
    鍦
    0.88
     көрс
    0.87
    ufl
    0.81
    ྥ
    0.79
    ামূলক
    0.78
    তার
    0.77
     pied
    0.77
    ToSend
    0.77
    Act Density 0.296%

    No Known Activations