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

    Neuronpedia

    INDEX
    Explanations

    making any decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realizar
    0.97
     formação
    0.92
     tabella
    0.92
     بالغ
    0.90
     ውስ
    0.90
     POLIT
    0.89
     elaborar
    0.88
     Biel
    0.87
    .¹
    0.86
     politic
    0.86
    POSITIVE LOGITS
    CHCl
    0.67
    return
    0.63
     div
    0.62
     cure
    0.61
     cured
    0.60
    Customer
    0.58
     same
    0.58
     curing
    0.58
     Humane
    0.58
    ဆ
    0.57
    Act Density 0.002%

    No Known Activations