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

    Neuronpedia

    INDEX
    Explanations

    organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LBL
    -0.07
    決定
    -0.07
    contri
    -0.06
    _matrices
    -0.06
    idden
    -0.06
     Oaks
    -0.06
    Highlights
    -0.06
     variant
    -0.06
    console
    -0.06
    .AddField
    -0.06
    POSITIVE LOGITS
     evac
    0.07
    /mp
    0.07
    xac
    0.07
    __);↵↵
    0.06
    종
    0.06
    	flags
    0.06
    escaping
    0.06
     shut
    0.06
    оч
    0.06
     collecting
    0.06
    Act Density 0.003%

    No Known Activations