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

    Neuronpedia

    INDEX
    Explanations

    artistic creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ممن
    0.38
     ব্রা
    0.37
    Brad
    0.36
    ባት
    0.36
    শাক
    0.35
    谯
    0.35
    MLB
    0.35
    ++];
    0.35
     dout
    0.34
    OPS
    0.34
    POSITIVE LOGITS
     creators
    1.07
     creatives
    1.02
     creativo
    0.98
     Creators
    0.96
     creative
    0.95
     creator
    0.93
     Creator
    0.87
    创作
    0.87
     твор
    0.86
     yarat
    0.86
    Act Density 0.105%

    No Known Activations