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

    Neuronpedia

    INDEX
    Explanations

    web framework unit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.36
    dale
    0.29
    matic
    0.29
    tedir
    0.28
    P
    0.28
    ych
    0.28
    Is
    0.28
    lma
    0.27
    '
    0.27
    inin
    0.26
    POSITIVE LOGITS
     for
    0.46
    ة
    0.39
    ли
    0.38
     syllable
    0.36
     két
    0.36
     topo
    0.35
     drake
    0.34
    ing
    0.34
     mít
    0.34
     marzo
    0.33
    Act Density 6.446%

    No Known Activations