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

    Neuronpedia

    INDEX
    Explanations

    ]]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '@
    -0.07
    YE
    -0.07
    love
    -0.06
     }),↵
    -0.06
     "{}
    -0.06
     PLEASE
    -0.06
    _NULL
    -0.06
    LTR
    -0.06
    _cmos
    -0.06
     Charger
    -0.06
    POSITIVE LOGITS
    climate
    0.08
    (state
    0.07
    inf
    0.06
    .platform
    0.06
    ophobic
    0.06
    字幕
    0.06
    optimized
    0.06
     adulthood
    0.06
     hs
    0.06
    olution
    0.06
    Act Density 0.011%

    No Known Activations