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

    Neuronpedia

    INDEX
    Explanations

    leadership titles

    np_acts-logits-general · gemini-2.5-flash-lite

    leadership roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    0.64
    د
    0.57
    t
    0.56
    た
    0.56
    д
    0.54
     is
    0.52
    ח
    0.51
    וי
    0.49
    บ
    0.49
    其他
    0.48
    POSITIVE LOGITS
     for
    0.70
    দের
    0.55
    ರ
    0.51
    મ
    0.50
    for
    0.50
    ㅋㅋ
    0.47
     emeritus
    0.47
    liğini
    0.46
     by
    0.45
     DPRD
    0.45
    Act Density 1.017%

    No Known Activations