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

    Neuronpedia

    INDEX
    Explanations

    chunk of text / unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sceptical
    0.49
    重
    0.46
    P
    0.43
    有
    0.41
    在
    0.41
     indire
    0.40
    ノ
    0.39
    争
    0.39
    극
    0.39
    That
    0.38
    POSITIVE LOGITS
    yka
    0.52
    খিক
    0.49
    icen
    0.48
    📠
    0.48
    er
    0.48
    ro
    0.47
    টারে
    0.46
     กิน
    0.45
    irsi
    0.45
     Frederick
    0.45
    Act Density 0.001%

    No Known Activations