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

    Neuronpedia

    INDEX
    Explanations

    unlimited, indefinite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SACTION
    -0.07
     currentValue
    -0.07
    	my
    -0.07
    扒
    -0.07
     Hyderabad
    -0.07
    getParameter
    -0.06
     הנוכ
    -0.06
     naw
    -0.06
    定向
    -0.06
    quant
    -0.06
    POSITIVE LOGITS
     KM
    0.08
     wires
    0.07
    𝘢
    0.07
     bert
    0.07
    🎗
    0.07
    Susp
    0.07
    OLD
    0.07
    orge
    0.07
    -deals
    0.07
    ôm
    0.07
    Act Density 0.148%

    No Known Activations