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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ਆਪਣ
    -0.08
     ਜੋ
    -0.08
     ڪم
    -0.08
     হত
    -0.08
     Fremont
    -0.08
     taong
    -0.08
     دعا
    -0.07
     జ
    -0.07
     постеп
    -0.07
     someone
    -0.07
    POSITIVE LOGITS
     (!)
    0.09
    )]
    0.09
    ？？
    0.08
     (?)
    0.08
    —not
    0.08
     incorrectly
    0.08
    ancis
    0.08
     wrongly
    0.08
    ???↵↵
    0.08
    ???
    0.08
    Act Density 0.061%

    No Known Activations