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

    Neuronpedia

    INDEX
    Explanations

    Technology articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Atlantis
    -0.28
    BAL
    -0.28
     fri
    -0.27
    åĦĨ
    -0.26
    Bag
    -0.26
     tink
    -0.26
    è°IJ
    -0.26
     ticking
    -0.26
    è¢ĭ
    -0.25
    indrome
    -0.25
    POSITIVE LOGITS
    éļIJå½¢
    0.29
    ihar
    0.26
    éļIJ
    0.26
    åľ³
    0.26
    æ¶Į
    0.26
    é²®
    0.25
    olds
    0.25
     roku
    0.25
    åĩºéģĵ
    0.25
     *}↵↵
    0.25
    Act Density 0.143%

    No Known Activations