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

    Neuronpedia

    INDEX
    Explanations

    dr. followed by period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    適切な
    0.38
    複数の
    0.37
    countery
    0.37
     технику
    0.37
    पर्य
    0.36
    SYSTEM
    0.36
    ，$
    0.36
    𒆠
    0.36
    เข้า
    0.36
    大量
    0.36
    POSITIVE LOGITS
     J
    0.53
     Z
    0.51
     T
    0.51
     O
    0.51
     D
    0.50
     L
    0.50
     N
    0.49
     E
    0.49
     G
    0.49
     B
    0.49
    Act Density 0.019%

    No Known Activations