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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     countert
    -0.08
    ега
    -0.07
     Claw
    -0.07
    	filter
    -0.07
     Fauc
    -0.07
    757
    -0.07
     엔
    -0.07
     chu
    -0.06
    Typed
    -0.06
     Benz
    -0.06
    POSITIVE LOGITS
     ActionType
    0.07
     Vue
    0.07
     مون
    0.07
     %↵
    0.06
     UObject
    0.06
     captcha
    0.06
    άνι
    0.06
    inant
    0.06
    λλην
    0.06
    ">&#
    0.06
    Act Density 0.043%

    No Known Activations