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

    Neuronpedia

    INDEX
    Explanations

    measurement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urved
    -0.07
    -data
    -0.06
    .$
    -0.06
     si
    -0.06
    ircles
    -0.06
    стин
    -0.06
    getSimpleName
    -0.06
    hões
    -0.06
    lates
    -0.06
     byli
    -0.06
    POSITIVE LOGITS
     puppy
    0.07
    	pp
    0.07
     กำ
    0.06
     PKK
    0.06
     jus
    0.06
    dice
    0.06
    	update
    0.06
     přístup
    0.06
     Puppy
    0.06
    delay
    0.06
    Act Density 0.000%

    No Known Activations