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

    Neuronpedia

    INDEX
    Explanations

    unplug from both

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    me
    0.96
    ma
    0.96
    по
    0.90
    meid
    0.82
    स
    0.81
    entions
    0.80
    ms
    0.79
    kaisi
    0.79
    str
    0.79
    tmp
    0.78
    POSITIVE LOGITS
     dekor
    0.79
     Billboard
    0.75
     prosec
    0.74
     dessin
    0.74
     Kantor
    0.74
     Chama
    0.74
     Celine
    0.73
     Jacinto
    0.73
     Vibes
    0.73
     Pilates
    0.72
    Act Density 0.020%

    No Known Activations