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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by commas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.87
     and
    0.61
     that
    0.58
     cote
    0.55
    ów
    0.51
    ка
    0.49
    t
    0.48
     rearing
    0.48
     cognizant
    0.47
    ă
    0.46
    POSITIVE LOGITS
    㓞
    0.60
    PAY
    0.53
    发射
    0.52
    idig
    0.52
    ELE
    0.52
    𠃊
    0.52
     volatil
    0.51
     })
    0.51
    创建一个
    0.51
     然后
    0.51
    Act Density 0.002%

    No Known Activations