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

    Neuronpedia

    INDEX
    Explanations

    minimum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     included
    -0.07
     newcomers
    -0.07
     GST
    -0.07
     EW
    -0.06
    /rules
    -0.06
    RICT
    -0.06
     sonra
    -0.06
    ardin
    -0.06
    pll
    -0.06
    Matthew
    -0.06
    POSITIVE LOGITS
    .Security
    0.06
     Org
    0.06
    �
    0.06
    "]["
    0.06
    线
    0.06
    $order
    0.06
    Ace
    0.06
    �
    0.06
    ecake
    0.06
    .gpu
    0.06
    Act Density 0.002%

    No Known Activations