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

    Neuronpedia

    INDEX
    Explanations

    connecting clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.70
    ?
    0.58
    !
    0.48
    :
    0.48
     ،
    0.47
    했지만
    0.46
    是什麼
    0.44
    ~
    0.44
    ،
    0.44
    .
    0.44
    POSITIVE LOGITS
     allowing
    0.72
     thereby
    0.67
    从而
    0.66
     जिससे
    0.63
     wodurch
    0.63
     ensuring
    0.63
     whereby
    0.62
     waardoor
    0.62
     resulting
    0.62
    これにより
    0.62
    Act Density 0.019%

    No Known Activations