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

    Neuronpedia

    INDEX
    Explanations

    assess behind rationalize market

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    av
    0.43
     breakaway
    0.43
    挞
    0.41
    esempio
    0.39
    quirements
    0.39
    শ্ব
    0.39
    Stor
    0.39
     کہانی
    0.39
    गिन
    0.38
    asant
    0.38
    POSITIVE LOGITS
     are
    0.50
    нию
    0.50
     s
    0.46
     other
    0.46
     pillows
    0.45
     actively
    0.45
     formulate
    0.44
    အား
    0.44
    安い
    0.44
     interacting
    0.42
    Act Density 0.001%

    No Known Activations