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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     supplies
    -0.07
    PEnd
    -0.07
     luôn
    -0.06
    Qui
    -0.06
    	REQUIRE
    -0.06
     wolf
    -0.06
    +x
    -0.06
     bracelet
    -0.06
    reeNode
    -0.06
     REF
    -0.06
    POSITIVE LOGITS
    lava
    0.07
     compos
    0.06
    assword
    0.06
    opathy
    0.06
     Ellie
    0.06
    گو
    0.06
    τιο
    0.06
    }_
    0.06
    имость
    0.06
     Roz
    0.06
    Act Density 0.031%

    No Known Activations