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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icensing
    -0.08
    章节
    -0.07
    Execution
    -0.07
    헠
    -0.07
     Structure
    -0.07
    &type
    -0.07
     CRE
    -0.07
    (extension
    -0.07
    ServerError
    -0.07
    GROUP
    -0.07
    POSITIVE LOGITS
    פי
    0.07
     distributions
    0.07
    琢磨
    0.07
    >`
    0.07
    _o
    0.07
     حول
    0.07
    坚持以
    0.06
    谟
    0.06
    	ct
    0.06
     jako
    0.06
    Act Density 0.052%

    No Known Activations