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

    Neuronpedia

    INDEX
    Explanations

    Comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _step
    -0.07
    됨
    -0.07
     lobbying
    -0.07
    .webdriver
    -0.07
     یافته
    -0.06
     openid
    -0.06
    _staff
    -0.06
    _Font
    -0.06
    건
    -0.06
    رير
    -0.06
    POSITIVE LOGITS
     Allocate
    0.07
    }"↵↵
    0.07
     티
    0.06
     Disp
    0.06
     rejuven
    0.06
    UIL
    0.06
     CHK
    0.06
    ा)
    0.06
    Disp
    0.06
    .Ad
    0.06
    Act Density 0.182%

    No Known Activations