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

    Neuronpedia

    INDEX
    Explanations

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stud
    -0.07
     Closure
    -0.07
    一步
    -0.07
     century
    -0.07
     aesthetics
    -0.06
    산업
    -0.06
    ict
    -0.06
     santa
    -0.06
     nuest
    -0.06
    Topics
    -0.06
    POSITIVE LOGITS
     though
    0.07
     BaseType
    0.06
     __________________________________
    0.06
     hvis
    0.06
    .Can
    0.06
    erseniz
    0.06
    pressive
    0.06
     Treasury
    0.06
    　　　　　　　　　　
    0.06
    though
    0.06
    Act Density 0.032%

    No Known Activations