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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     woo
    -0.07
     McCain
    -0.06
    kills
    -0.06
     pregnant
    -0.06
    igung
    -0.06
     planner
    -0.06
     HOT
    -0.06
     같
    -0.06
    ाट
    -0.06
     sends
    -0.06
    POSITIVE LOGITS
    ávky
    0.07
    useRalative
    0.06
    =r
    0.06
    	Vector
    0.06
     communion
    0.06
    /(
    0.06
    =B
    0.06
    říž
    0.06
     언
    0.06
     фін
    0.06
    Act Density 0.041%

    No Known Activations