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

    Neuronpedia

    INDEX
    Explanations

    Excerpts of larger documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     subtract
    -0.07
    通信
    -0.06
    putation
    -0.06
     ноги
    -0.06
    -engine
    -0.06
     Brent
    -0.06
     CAL
    -0.06
     greedy
    -0.06
     mish
    -0.06
    $search
    -0.06
    POSITIVE LOGITS
     aliqua
    0.07
    톡
    0.06
     Dumpster
    0.06
     colorWith
    0.06
     rested
    0.06
    quiv
    0.06
     getSupportActionBar
    0.06
    書館
    0.06
     운동
    0.06
    '=>$
    0.06
    Act Density 0.292%

    No Known Activations