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

    Neuronpedia

    INDEX
    Explanations

    code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esempio
    0.42
     exemple
    0.40
     ??
    0.39
     πάντα
    0.39
     Interesting
    0.39
     Puzzle
    0.39
    ٫
    0.39
     tho
    0.39
    してる
    0.39
     ৷
    0.38
    POSITIVE LOGITS
    Alternatives
    0.45
    Alternatively
    0.43
    提供
    0.40
    我可以
    0.40
     неско
    0.38
    iries
    0.38
    ALTERNATIV
    0.37
    অথ
    0.37
    commutative
    0.37
    几个
    0.37
    Act Density 0.006%

    No Known Activations