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

    Neuronpedia

    INDEX
    Explanations

    output characteristics and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ૧
    0.49
     viol
    0.49
    ាល់
    0.49
     ban
    0.48
    োই
    0.48
    ޏ
    0.47
     স্বাভাবিক
    0.47
     paramount
    0.46
     दाग
    0.46
    ाया
    0.46
    POSITIVE LOGITS
    Adder
    0.45
     جھنڈ
    0.44
    ights
    0.44
    Geography
    0.43
    生命
    0.42
     ফিল্ম
    0.41
     expériment
    0.41
    binary
    0.40
    Throttle
    0.40
     аў
    0.40
    Act Density 0.000%

    No Known Activations