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

    Neuronpedia

    INDEX
    Explanations

    care, game, printing, video

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.42
     входит
    0.40
    濫
    0.40
     원래
    0.39
     входят
    0.39
     XRD
    0.39
    장은
    0.38
    сто
    0.37
    d
    0.37
    xyz
    0.36
    POSITIVE LOGITS
     mee
    0.49
     erkennen
    0.49
     amélior
    0.48
     videog
    0.46
    améliorer
    0.45
    Rash
    0.45
    linkColor
    0.45
     améliorer
    0.44
     pape
    0.44
     entdecken
    0.44
    Act Density 0.002%

    No Known Activations