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

    Neuronpedia

    INDEX
    Explanations

    R code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تار
    0.40
     omnis
    0.39
    धिकरण
    0.38
    Visited
    0.38
     Rwand
    0.38
    0.38
    燭
    0.36
    ہے
    0.36
     searchObject
    0.35
     concluding
    0.35
    POSITIVE LOGITS
    source
    0.57
    "%
    0.54
     source
    0.51
     Source
    0.49
    '%
    0.48
    源
    0.47
    Source
    0.47
    make
    0.43
    getSource
    0.43
     SOURCE
    0.43
    Act Density 0.005%

    No Known Activations