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

    Neuronpedia

    INDEX
    Explanations

    Endless running games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    首次
    -0.09
     rationale
    -0.08
     opgelost
    -0.08
     remedy
    -0.08
    ELEMENT
    -0.08
    cedence
    -0.07
     exécut
    -0.07
     제작
    -0.07
     aanleiding
    -0.07
     tann
    -0.07
    POSITIVE LOGITS
     continuously
    0.09
    不断
    0.09
     endless
    0.09
    高速
    0.09
     Endless
    0.09
    不中
    0.08
     forever
    0.08
     unstoppable
    0.08
     Styl
    0.08
    צלחה
    0.08
    Act Density 0.008%

    No Known Activations