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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     veces
    -0.07
     Bosch
    -0.06
    Mc
    -0.06
     overwhelmed
    -0.06
     <
    -0.06
     reels
    -0.06
     dull
    -0.06
     keypoints
    -0.05
     Percentage
    -0.05
     Mc
    -0.05
    POSITIVE LOGITS
     아이디
    0.08
    globals
    0.07
     prejud
    0.07
    нии
    0.07
     complied
    0.07
    __':
↵
    0.07
    0
    0.07
     сегодня
    0.06
    $I
    0.06
    .changed
    0.06
    Act Density 0.038%

    No Known Activations