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

    Neuronpedia

    INDEX
    Explanations

    class, Kla, Clo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonatomic
    0.40
    icionar
    0.38
    ucionales
    0.37
     รวมถึง
    0.37
    ސް
    0.36
     arrhyth
    0.36
     konflikt
    0.36
    েন্দ
    0.36
     промежу
    0.36
     গ্রাম
    0.35
    POSITIVE LOGITS
     Cla
    0.50
    Cla
    0.46
    cla
    0.40
     kla
    0.39
    cale
    0.37
     [][]
    0.36
     cla
    0.36
     Kla
    0.36
     Clo
    0.36
    indle
    0.35
    Act Density 0.002%

    No Known Activations