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

    Neuronpedia

    INDEX
    Explanations

    shell commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bcc
    -0.07
     Negro
    -0.07
     Negative
    -0.07
    톡
    -0.06
    petition
    -0.06
     score
    -0.06
    -prof
    -0.06
     talk
    -0.06
    .play
    -0.06
     Israel
    -0.06
    POSITIVE LOGITS
     deletes
    0.07
    กล
    0.07
    "</
    0.07
     mutableListOf
    0.06
     smtp
    0.06
    WEBPACK
    0.06
     المج
    0.06
    :flutter
    0.06
    uyla
    0.06
    ').'</
    0.06
    Act Density 0.001%

    No Known Activations