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

    Neuronpedia

    INDEX
    Explanations

    complex and evolving topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.43
     an
    0.41
     is
    0.39
     represents
    0.35
     becomes
    0.34
    '
    0.32
     has
    0.32
    the
    0.32
     является
    0.31
     the
    0.30
    POSITIVE LOGITS
     ইতিহাস
    0.25
     ważne
    0.25
    بہ
    0.24
     odlič
    0.24
     понять
    0.23
     মতামত
    0.23
     kõik
    0.23
     فهم
    0.23
     całej
    0.23
     ovako
    0.23
    Act Density 0.206%

    No Known Activations