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

    Neuronpedia

    INDEX
    Explanations

    Such [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Этот
    0.49
     وكان
    0.44
     this
    0.43
     В
    0.42
     sadece
    0.41
     Кон
    0.41
    ايا
    0.41
     कुल
    0.40
    <0xF3>
    0.40
     the
    0.39
    POSITIVE LOGITS
     applications
    0.52
     therapies
    0.49
     idées
    0.47
     ideas
    0.46
     purchases
    0.45
     premiums
    0.44
     utterances
    0.44
     creations
    0.43
     aplicações
    0.43
     actions
    0.42
    Act Density 0.004%

    No Known Activations