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

    Neuronpedia

    INDEX
    Explanations

    , the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     здрав
    0.39
     wyłącznie
    0.39
    etri
    0.38
    வதில்லை
    0.36
     Contracting
    0.36
    டும்ப
    0.35
     esclusivamente
    0.35
     सुद्धा
    0.35
     क्या
    0.34
    کاری
    0.34
    POSITIVE LOGITS
     desto
    1.16
    thebetter
    0.91
    수록
    0.87
    ยิ่ง
    0.78
     ততই
    0.77
    越高
    0.77
    越多
    0.73
     better
    0.73
     càng
    0.71
    越大
    0.68
    Act Density 0.010%

    No Known Activations