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

    Neuronpedia

    INDEX
    Explanations

    uses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     STOP
    -0.07
    ику
    -0.07
    ività
    -0.06
    uale
    -0.06
    Ray
    -0.06
     destroy
    -0.06
    shipment
    -0.06
    itory
    -0.06
     controlling
    -0.06
    احل
    -0.06
    POSITIVE LOGITS
     Rover
    0.07
     separ
    0.07
     conferences
    0.06
     banco
    0.06
    /el
    0.06
     circumference
    0.06
     Bella
    0.06
     el
    0.06
    -components
    0.06
    –and
    0.06
    Act Density 0.000%

    No Known Activations