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

    Neuronpedia

    INDEX
    Explanations

    new concepts or stages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    doesn
    0.45
    but
    0.38
    uuuu
    0.38
    也就是说
    0.37
    aaaa
    0.37
    And
    0.36
    aaaaaaaa
    0.36
     whose
    0.36
    🤣🤣
    0.35
    気に入
    0.35
    POSITIVE LOGITS
     नए
    0.35
     ಸಮ
    0.35
     νέ
    0.35
     kēia
    0.33
     ಹೊಸ
    0.32
     etapas
    0.32
    striatis
    0.32
     émer
    0.31
     nuevas
    0.31
     özel
    0.31
    Act Density 0.018%

    No Known Activations