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

    Neuronpedia

    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benefits
    -0.07
    -wife
    -0.06
     Exp
    -0.06
     reports
    -0.06
     playoff
    -0.06
     pari
    -0.06
     Morg
    -0.06
    Date
    -0.06
     thirds
    -0.06
    Proj
    -0.06
    POSITIVE LOGITS
    [,
    0.08
     
    0.07
    ossier
    0.07
    英雄
    0.07
    .XRLabel
    0.06
    비스
    0.06
    搭
    0.06
     �
    0.06
    册
    0.06
     PIXI
    0.06
    Act Density 0.079%

    No Known Activations