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

    Neuronpedia

    INDEX
    Explanations

    uses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SHIFT
    -0.07
    ENTRY
    -0.06
    "}),↵
    -0.06
    抬起
    -0.06
    Paste
    -0.06
     ++)↵
    -0.06
    年纪
    -0.06
     settling
    -0.06
    Ⲉ
    -0.06
    erre
    -0.06
    POSITIVE LOGITS
    (user
    0.07
     deadly
    0.07
    车联网
    0.07
    pdf
    0.07
    쬐
    0.06
    -home
    0.06
    URRENCY
    0.06
     очеред
    0.06
     Rihanna
    0.06
     лид
    0.06
    Act Density 0.001%

    No Known Activations