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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç³ħ
    -0.29
    è¿Ľåº¦
    -0.28
     keyboards
    -0.28
    reator
    -0.27
     dads
    -0.25
    AXB
    -0.25
    éĤ£ä»½
    -0.25
     Fathers
    -0.25
    $ar
    -0.25
     planners
    -0.24
    POSITIVE LOGITS
    æĴ¤éĶĢ
    0.28
    代价
    0.28
    ulo
    0.28
    zing
    0.25
    èĨ¨èĥĢ
    0.25
     unc
    0.24
    å¿ħè¦ģ
    0.24
    ering
    0.24
    /pkg
    0.24
     Paging
    0.24
    Act Density 0.805%

    No Known Activations