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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IRS
    -0.06
    atten
    -0.06
    accel
    -0.06
     Ras
    -0.06
    πως
    -0.06
    .Score
    -0.06
     emblem
    -0.06
    outputs
    -0.06
    rios
    -0.06
    59
    -0.06
    POSITIVE LOGITS
     TODAY
    0.07
     rež
    0.06
    	property
    0.06
    cribed
    0.06
     Základní
    0.06
    ///
↵
    0.06
    iguous
    0.06
     (){↵
    0.06
    ;;;
    0.06
    _levels
    0.06
    Act Density 0.010%

    No Known Activations