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

    Neuronpedia

    INDEX
    Explanations

    me

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prvním
    -0.08
     POD
    -0.07
     Rajasthan
    -0.06
     Staten
    -0.06
    뮤
    -0.06
    /Header
    -0.06
    Initialization
    -0.06
    INSTANCE
    -0.06
    ğında
    -0.06
    δό
    -0.06
    POSITIVE LOGITS
     Leban
    0.06
    .am
    0.06
    变得
    0.06
    urb
    0.06
    /manual
    0.06
    elay
    0.06
    _codes
    0.06
    _can
    0.06
     matchup
    0.06
    [,
    0.06
    Act Density 0.000%

    No Known Activations