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

    Neuronpedia

    INDEX
    Explanations

    this patient, Disclaimer, Understanding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ିକ
    0.43
    Fen
    0.41
     injection
    0.41
    cycle
    0.40
    ীয়
    0.39
    收集
    0.39
    Dar
    0.39
     ovar
    0.39
    Bac
    0.39
    beyond
    0.39
    POSITIVE LOGITS
     precio
    0.51
    '<
    0.50
    '
    0.49
     coisas
    0.49
     aumento
    0.48
    '",
    0.48
     dinero
    0.48
     certos
    0.48
     campo
    0.47
     its
    0.47
    Act Density 0.000%

    No Known Activations