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

    Neuronpedia

    INDEX
    Explanations

    understanding and linking concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或其他
    0.44
     등으로
    0.44
    などに
    0.43
    などを
    0.43
     usw
    0.40
     등을
    0.40
     등에
    0.40
     beserta
    0.39
    などが
    0.39
     etc
    0.38
    POSITIVE LOGITS
    并
    0.80
    并在
    0.69
     وتن
    0.55
    maintain
    0.54
    analyze
    0.53
    然后在
    0.52
     وتح
    0.51
     and
    0.51
     وت
    0.51
     और
    0.50
    Act Density 0.064%

    No Known Activations