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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hill
    -0.08
     Rain
    -0.08
     gray
    -0.08
     Brown
    -0.08
    ilin
    -0.07
     radically
    -0.07
     wind
    -0.07
     Wind
    -0.07
     rack
    -0.07
     Irr
    -0.07
    POSITIVE LOGITS
     подоб
    0.09
     tog
    0.08
     salope
    0.08
     Loy
    0.07
     "<?
    0.07
    208
    0.07
     підс
    0.07
    .spi
    0.07
    股份有限公司
    0.07
    ')?>
    0.07
    Act Density 0.085%

    No Known Activations