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

    Neuronpedia

    INDEX
    Explanations

    bloc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =val
    -0.08
     doses
    -0.08
    长相
    -0.07
    놉
    -0.07
    /update
    -0.07
     unde
    -0.07
    .groups
    -0.07
    condition
    -0.07
     Airport
    -0.07
    леж
    -0.07
    POSITIVE LOGITS
    .userInfo
    0.07
     passionate
    0.07
    채
    0.07
     הרב
    0.06
    .Skin
    0.06
     troubleshooting
    0.06
    私人
    0.06
     french
    0.06
    	REG
    0.06
    快讯
    0.06
    Act Density 0.005%

    No Known Activations