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

    Neuronpedia

    INDEX
    Explanations

    contrast and qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ということです
    0.39
    Lad
    0.36
    没有任何
    0.36
     Plut
    0.36
     Lad
    0.35
     amply
    0.35
     brut
    0.35
    经历
    0.35
     Brut
    0.35
     දැන්
    0.34
    POSITIVE LOGITS
    でしたが
    1.05
     nhưng
    0.93
     but
    0.91
    했지만
    0.91
     ولكن
    0.88
     lakini
    0.88
     แต่
    0.87
    but
    0.86
     लेकिन
    0.86
    なのですが
    0.85
    Act Density 0.139%

    No Known Activations