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

    Neuronpedia

    INDEX
    Explanations

    dominance ordering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autoWatch
    0.58
    䣼
    0.49
    acyjnego
    0.48
     expliqué
    0.46
     Speck
    0.46
     ευρώ
    0.46
     Ελλά
    0.45
     સુ
    0.45
     Är
    0.45
    जनिक
    0.44
    POSITIVE LOGITS
    m
    0.61
    i
    0.60
    c
    0.55
    range
    0.51
    ong
    0.51
    e
    0.50
    switch
    0.49
     of
    0.48
    x
    0.48
    twenty
    0.48
    Act Density 0.000%

    No Known Activations