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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fusion
    -0.06
    .content
    -0.06
     VLAN
    -0.06
    _prices
    -0.06
    LEY
    -0.06
    كية
    -0.06
    Element
    -0.06
    riot
    -0.06
    	verify
    -0.06
    setLabel
    -0.06
    POSITIVE LOGITS
    .Source
    0.06
    anding
    0.06
     Brooklyn
    0.06
    ">'.
    0.06
     unaware
    0.06
    Gab
    0.06
    "B
    0.06
     dokon
    0.06
     master
    0.06
     ');↵↵
    0.06
    Act Density 0.187%

    No Known Activations