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

    Neuronpedia

    INDEX
    Explanations

    rev

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _boundary
    -0.06
     Γι
    -0.06
    竹
    -0.06
     Marc
    -0.06
     coord
    -0.05
     Samp
    -0.05
     mamm
    -0.05
     bears
    -0.05
    .dll
    -0.05
     animals
    -0.05
    POSITIVE LOGITS
    	want
    0.08
     spokes
    0.07
    .Inventory
    0.07
     Review
    0.06
     surviv
    0.06
    SPELL
    0.06
    ｀
    0.06
    .ForeignKey
    0.06
    ＾
    0.06
     redux
    0.06
    Act Density 0.013%

    No Known Activations