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

    Neuronpedia

    INDEX
    Explanations

    distant land

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    and
    0.70
     prosecution
    0.58
    н
    0.57
    lack
    0.55
     suppuration
    0.54
    この記事
    0.53
    न
    0.53
    ন
    0.53
    lc
    0.51
    お手
    0.50
    POSITIVE LOGITS
     is
    0.62
    {
    0.55
     Doc
    0.55
    鱿
    0.53
     的
    0.52
     พ
    0.51
    辰
    0.49
     ச
    0.49
     abhid
    0.49
    ሱን
    0.47
    Act Density 0.000%

    No Known Activations