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

    Neuronpedia

    INDEX
    Explanations

    JavaScript and Python programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وا
    0.38
     MO
    0.31
     DU
    0.30
     ACO
    0.30
     LU
    0.30
    Glu
    0.30
     ISO
    0.29
     in
    0.29
     JU
    0.28
     HL
    0.28
    POSITIVE LOGITS
    isać
    0.37
     xhrObj
    0.36
     '';
    0.36
     [];
    0.35
    pager
    0.34
    <unused2155>
    0.34
     ដើម្បី
    0.34
     நடிக
    0.33
     विधान
    0.33
    जिस
    0.33
    Act Density 0.050%

    No Known Activations