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

    Neuronpedia

    INDEX
    Explanations

    while

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ene
    -0.28
    æīĢåľ¨
    -0.27
     behalf
    -0.27
    åĪ»
    -0.27
     factorial
    -0.26
    D
    -0.25
    åĨĽ
    -0.24
    alm
    -0.24
    Ĥ¬
    -0.24
     hand
    -0.23
    POSITIVE LOGITS
     jams
    0.27
    è¿IJæ°Ķ
    0.27
    reste
    0.27
    CHASE
    0.27
    ifique
    0.26
    ÃŃst
    0.26
    ajan
    0.25
     Zucker
    0.25
    rese
    0.25
    gtest
    0.25
    Act Density 0.140%

    No Known Activations