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

    Neuronpedia

    INDEX
    Explanations

    scissors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [*
    -0.07
    Clients
    -0.07
    /header
    -0.07
     clique
    -0.07
    Vm
    -0.07
    ’.↵↵
    -0.07
    的最大
    -0.06
     west
    -0.06
     pulses
    -0.06
    州
    -0.06
    POSITIVE LOGITS
    arily
    0.08
    ᴈ
    0.07
    $product
    0.07
    	sound
    0.07
     didn
    0.07
    -than
    0.07
     Entertainment
    0.07
     hilarious
    0.07
    ,Y
    0.07
    aría
    0.07
    Act Density 0.001%

    No Known Activations