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

    Neuronpedia

    INDEX
    Explanations

    verbs related to states of being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     up
    1.08
    బడి
    0.79
    화
    0.77
     שע
    0.72
    مر
    0.72
     ధ
    0.69
     recycled
    0.68
    cane
    0.68
     مفت
    0.68
    जिब
    0.67
    POSITIVE LOGITS
     eigenlijk
    0.91
    Storage
    0.91
    Elemental
    0.88
    Ordine
    0.87
     പ്രാ
    0.83
    Move
    0.82
    Numbers
    0.80
    storage
    0.80
    Qualified
    0.79
    Pedido
    0.79
    Act Density 0.001%

    No Known Activations