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

    Neuronpedia

    INDEX
    Explanations

    Douglas Adams, dynamic programming, dangerous

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    בי
    0.52
    企業
    0.51
    總
    0.51
    tel
    0.45
     athlet
    0.45
    企业
    0.45
    全球
    0.45
    రంగ
    0.44
    世界杯
    0.44
    氨
    0.44
    POSITIVE LOGITS
     hindrance
    0.52
     изменить
    0.50
     wrinkled
    0.50
     Необходимо
    0.49
     LIGO
    0.48
     hypothesized
    0.47
     prudence
    0.47
     ноги
    0.47
    stuhl
    0.47
     sows
    0.47
    Act Density 0.000%

    No Known Activations