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

    Neuronpedia

    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     réfugi
    -0.49
     joyas
    -0.49
     fjor
    -0.48
     tromper
    -0.48
     gouttes
    -0.47
     vastaan
    -0.46
     compét
    -0.46
     aveug
    -0.46
     biens
    -0.45
     gånger
    -0.45
    POSITIVE LOGITS
    aryen
    0.76
     Roskov
    0.75
     noqa
    0.72
     ProtoMessage
    0.72
     doInBackground
    0.71
    tvguidetime
    0.70
    AdapterView
    0.70
    ---*/
    0.68
    تقاوى
    0.68
    Życiorys
    0.65
    Act Density 0.011%

    No Known Activations