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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    зі
    -0.07
    ência
    -0.06
     trivia
    -0.06
    -Nov
    -0.06
    nutí
    -0.06
     registers
    -0.06
     учеб
    -0.06
     Robot
    -0.06
    vary
    -0.05
     cousins
    -0.05
    POSITIVE LOGITS
    \",\
    0.07
    イズ
    0.07
    cla
    0.07
    midd
    0.07
    (Role
    0.07
     addslashes
    0.07
    Id
    0.07
    ‫
    0.07
    locks
    0.07
     createState
    0.06
    Act Density 0.002%

    No Known Activations