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

    Neuronpedia

    INDEX
    Explanations

    purposes only

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रतिनिधित्व
    0.81
    خدام
    0.80
    条件
    0.78
     Quezon
    0.77
     України
    0.76
    客户端
    0.76
    ριν
    0.75
    Diagram
    0.73
     우리가
    0.73
    ρού
    0.73
    POSITIVE LOGITS
     gust
    0.77
     leaves
    0.76
     gusts
    0.73
     delighted
    0.68
    markt
    0.65
     deserted
    0.65
    leaves
    0.65
     perfectly
    0.64
     leaf
    0.64
     left
    0.63
    Act Density 0.000%

    No Known Activations