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

    Neuronpedia

    INDEX
    Explanations

    setup and completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ontvang
    0.74
     предлагает
    0.73
    시키는
    0.72
    арма
    0.71
     كانت
    0.68
    寻求
    0.67
     принимает
    0.64
    小的
    0.63
    将其
    0.62
    Finding
    0.62
    POSITIVE LOGITS
     sorted
    1.60
     installed
    1.55
     reinstated
    1.51
     shoved
    1.49
     delivered
    1.45
     done
    1.43
     cleared
    1.43
     evaluated
    1.38
     ready
    1.37
     implemented
    1.35
    Act Density 0.146%

    No Known Activations