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

    Neuronpedia

    INDEX
    Explanations

    address

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CentOS
    -0.06
     خوبی
    -0.06
    apsible
    -0.06
    Connections
    -0.06
     philosoph
    -0.06
     fines
    -0.06
     ADHD
    -0.06
     edges
    -0.06
     الأف
    -0.06
     created
    -0.06
    POSITIVE LOGITS
     prv
    0.07
    fel
    0.07
     probable
    0.06
    Trim
    0.06
    _encode
    0.06
    rule
    0.06
    -dev
    0.06
    etim
    0.06
    े.
    0.06
     energetic
    0.06
    Act Density 0.002%

    No Known Activations