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

    Neuronpedia

    INDEX
    Explanations

    company names or "called" follow-ups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಂಟು
    0.44
     کہانی
    0.44
    経験
    0.43
    ০০
    0.42
     unsuccessful
    0.42
    われる
    0.42
    長期
    0.41
    cluded
    0.40
    બાદ
    0.40
    最初の
    0.39
    POSITIVE LOGITS
     Microsoft
    0.55
     Oracle
    0.47
     Sign
    0.47
    icrosoft
    0.46
    /
    0.46
     Verizon
    0.45
     Comcast
    0.44
    ş
    0.43
     Dere
    0.43
     microsoft
    0.42
    Act Density 0.002%

    No Known Activations