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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pour
    -0.07
     disciple
    -0.07
    '))↵↵↵
    -0.07
     resumed
    -0.06
    ('../
    -0.06
    潆
    -0.06
    .Location
    -0.06
     Smithsonian
    -0.06
     것도
    -0.06
    /Desktop
    -0.06
    POSITIVE LOGITS
    FLASH
    0.07
    噼
    0.07
    reward
    0.07
     rozwiązania
    0.07
    四个
    0.07
     müdahale
    0.06
     ters
    0.06
     autoc
    0.06
     yük
    0.06
    应急预案
    0.06
    Act Density 0.082%

    No Known Activations