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

    Neuronpedia

    INDEX
    Explanations

    error reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jahr
    0.41
     postav
    0.41
     개
    0.41
     આપી
    0.40
    ۆر
    0.39
    imizi
    0.38
     করল
    0.38
     kullanılır
    0.38
     které
    0.37
    样的
    0.37
    POSITIVE LOGITS
     unable
    0.60
     नहीं
    0.57
     refrained
    0.54
     unsuccessful
    0.54
     lacks
    0.53
     inability
    0.53
     unwillingness
    0.50
     lacked
    0.50
     không
    0.49
     WARNING
    0.48
    Act Density 0.029%

    No Known Activations