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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hostel
    -0.07
    Mexico
    -0.07
     unmatched
    -0.07
     announces
    -0.06
    pictures
    -0.06
     Policies
    -0.06
    ilateral
    -0.06
     світі
    -0.06
     peak
    -0.06
    -label
    -0.06
    POSITIVE LOGITS
     opr
    0.07
    αρ
    0.07
     from
    0.07
     通
    0.07
     adipisicing
    0.07
    leaflet
    0.07
     bodyParser
    0.06
     referee
    0.06
     дер
    0.06
     overridden
    0.06
    Act Density 0.015%

    No Known Activations