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

    Neuronpedia

    INDEX
    Explanations

    trained on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ামি
    0.52
    它們
    0.52
    正好
    0.50
    larınız
    0.50
     secreted
    0.50
    但是我
    0.49
     mislead
    0.49
    ErrorException
    0.48
    erialize
    0.48
     darken
    0.48
    POSITIVE LOGITS
     Historically
    0.66
     عليه
    0.59
     AGRICULTURAL
    0.58
     ज्यामुळे
    0.57
    MADE
    0.57
    በት
    0.57
    颔
    0.56
     інформа
    0.55
     hiszen
    0.55
     radiological
    0.55
    Act Density 0.018%

    No Known Activations