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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拿起
    -0.07
     BlackBerry
    -0.07
     impressed
    -0.07
     Raymond
    -0.07
    patrick
    -0.07
     ([[
    -0.07
     partisan
    -0.06
     cleared
    -0.06
    党组
    -0.06
     compelled
    -0.06
    POSITIVE LOGITS
    棁
    0.08
    סל
    0.07
    ﮰ
    0.07
    _temperature
    0.07
    ALSE
    0.07
     CO
    0.07
    _ac
    0.07
     laure
    0.07
    벚
    0.07
    נטר
    0.07
    Act Density 0.128%

    No Known Activations