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

    Neuronpedia

    INDEX
    Explanations

    scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chat
    -0.07
     Chunk
    -0.06
    Clazz
    -0.06
    	public
    -0.06
    plan
    -0.06
    polygon
    -0.06
     grosse
    -0.06
    LOOK
    -0.06
     Chat
    -0.06
     pog
    -0.06
    POSITIVE LOGITS
    (Context
    0.08
    */↵
    0.07
     darkness
    0.06
    ————————
    0.06
    toUpperCase
    0.06
    лина
    0.06
    iverse
    0.06
    장
    0.06
    dq
    0.06
    /Footer
    0.06
    Act Density 0.286%

    No Known Activations