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

    Neuronpedia

    INDEX
    Explanations

    wants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ENTER
    -0.09
     DevComponents
    -0.08
     DeV
    -0.07
    되지
    -0.07
    无关
    -0.07
    鹚
    -0.07
    .Collections
    -0.07
     appears
    -0.07
    そういう
    -0.07
    ในฐาน
    -0.06
    POSITIVE LOGITS
     wipe
    0.09
     coalition
    0.08
     ks
    0.08
     microwave
    0.07
     timeline
    0.07
     Egypt
    0.07
    链
    0.07
     Tokyo
    0.07
    ♪
    0.07
    _shortcode
    0.07
    Act Density 0.059%

    No Known Activations