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

    Neuronpedia

    INDEX
    Explanations

    tasks actions perform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .R
    -0.07
     enumeration
    -0.07
     notifications
    -0.07
    uffling
    -0.06
     сет
    -0.06
     R
    -0.06
    (),↵
    -0.06
     R
    -0.06
    discussion
    -0.06
     undisclosed
    -0.06
    POSITIVE LOGITS
    lovak
    0.07
    τηγορία
    0.06
    (module
    0.06
     福
    0.06
    γον
    0.06
     أخ
    0.06
    (ptr
    0.06
    grim
    0.06
    aroo
    0.06
    �
    0.06
    Act Density 0.051%

    No Known Activations