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

    Neuronpedia

    INDEX
    Explanations

    instructions, partnerships, building intensity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     junge
    0.54
     کې
    0.49
     discurso
    0.48
     desempeñ
    0.47
     encuentro
    0.47
     múltipl
    0.47
     ایالات
    0.46
    UFACT
    0.46
     cercanas
    0.46
     principio
    0.46
    POSITIVE LOGITS
     Peach
    0.54
     Don
    0.50
     Aging
    0.49
    owers
    0.49
    ers
    0.48
     Honda
    0.47
     Jan
    0.47
     their
    0.46
     Autumn
    0.46
     assassins
    0.46
    Act Density 0.000%

    No Known Activations