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

    Neuronpedia

    INDEX
    Explanations

    leadership and management roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.52
     ఇ
    0.48
    д
    0.47
     మనం
    0.47
     ఉపయోగ
    0.47
     ము
    0.46
     រ
    0.46
     ذلك
    0.46
     నె
    0.45
     ఇప్పుడు
    0.45
    POSITIVE LOGITS
     for
    0.65
    મ
    0.52
    ство
    0.52
    کار
    0.49
    ’
    0.49
    for
    0.48
    کل
    0.48
    B
    0.48
    ರ
    0.46
    کن
    0.45
    Act Density 0.207%

    No Known Activations