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

    Neuronpedia

    INDEX
    Explanations

    distributed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    反应
    -0.06
    .REQUEST
    -0.06
    _reviews
    -0.06
     Answer
    -0.06
     MAK
    -0.06
     eggs
    -0.06
     divul
    -0.06
     lưới
    -0.06
     recur
    -0.06
    .argmax
    -0.05
    POSITIVE LOGITS
    學
    0.07
    __.'/
    0.07
     Buen
    0.07
     askeri
    0.07
     conveniently
    0.06
     exists
    0.06
    ecessarily
    0.06
    つぶ
    0.06
     Buddha
    0.06
    σμό
    0.06
    Act Density 0.001%

    No Known Activations