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

    Neuronpedia

    INDEX
    Explanations

    federal government regulatory agencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bö
    0.73
     KDE
    0.69
     Héctor
    0.68
     HCC
    0.65
     će
    0.65
     hulls
    0.64
     KNN
    0.63
     Kõ
    0.63
     GMA
    0.63
     Jürgen
    0.62
    POSITIVE LOGITS
    ור
    0.73
    yn
    0.64
    liche
    0.61
    elekt
    0.60
    ב
    0.59
    */
    0.58
    hyd
    0.57
    П
    0.57
    garakan
    0.55
    realpath
    0.55
    Act Density 0.143%

    No Known Activations