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

    Neuronpedia

    INDEX
    Explanations

    Times New Roman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.52
     photons
    0.49
     sedang
    0.49
    ı
    0.47
     curves
    0.46
     Japanese
    0.46
     periods
    0.46
    );
    0.45
     motifs
    0.45
    ญี่ปุ่น
    0.45
    POSITIVE LOGITS
     سي
    0.60
    er
    0.59
     なかっ
    0.57
    ت
    0.55
    sene
    0.54
    WindowClass
    0.54
     سانت
    0.54
    ed
    0.54
    čené
    0.54
    on
    0.53
    Act Density 0.000%

    No Known Activations