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

    Neuronpedia

    INDEX
    Explanations

    summarize information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    퀴
    0.46
    Cu
    0.45
     cu
    0.41
     Cody
    0.39
     Gu
    0.38
     advances
    0.37
     Shr
    0.37
    cu
    0.37
     Cu
    0.36
     nu
    0.36
    POSITIVE LOGITS
    🟣
    0.45
    idać
    0.42
     opcion
    0.42
    款式
    0.41
    coloured
    0.40
    𒊹
    0.40
    ）；
    0.40
    ोटोरोला
    0.39
    冇
    0.39
     festge
    0.39
    Act Density 0.001%

    No Known Activations