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
    manent
    -0.07
     Biggest
    -0.07
    (outfile
    -0.06
    NEG
    -0.06
     Kids
    -0.06
     gravity
    -0.06
    it
    -0.06
     بزرگ
    -0.06
    Requests
    -0.06
    είτε
    -0.06
    POSITIVE LOGITS
     cose
    0.06
    _migration
    0.06
     ditch
    0.06
     ****************
    0.06
    érieur
    0.06
    payer
    0.06
     فق
    0.06
    .ToolStripItem
    0.06
     overlay
    0.06
     Cafe
    0.06
    Act Density 0.000%

    No Known Activations