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

    Neuronpedia

    INDEX
    Explanations

    process descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dim
    -0.07
    	A
    -0.07
    -Out
    -0.07
     Clayton
    -0.07
     railing
    -0.07
     Studio
    -0.07
    atham
    -0.07
     Organ
    -0.06
    MAX
    -0.06
     Stat
    -0.06
    POSITIVE LOGITS
    .getCell
    0.07
    /sl
    0.07
     samen
    0.06
    raně
    0.06
    纯
    0.06
     ）
    0.06
     викон
    0.06
     порядку
    0.06
    yps
    0.06
    _ComCallableWrapper
    0.06
    Act Density 0.008%

    No Known Activations