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

    Neuronpedia

    INDEX
    Explanations

    sentence breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     потому
    0.27
    Because
    0.26
     because
    0.26
    Fortunately
    0.25
    เพราะ
    0.24
     puisqu
    0.24
     porque
    0.24
     BECAUSE
    0.23
    because
    0.23
    因為
    0.22
    POSITIVE LOGITS
    vering
    0.22
    oco
    0.21
     ज्यामुळे
    0.21
     दोन्ही
    0.20
     Dadurch
    0.20
    offs
    0.20
     ಇದರಿಂದ
    0.19
    herent
    0.19
    zelfde
    0.19
    riel
    0.19
    Act Density 0.108%

    No Known Activations