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

    Neuronpedia

    INDEX
    Explanations

    often Friday Evening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tendencia
    0.48
     pieces
    0.45
     military
    0.44
     complacency
    0.43
     invited
    0.43
     The
    0.42
     tiros
    0.42
    インド
    0.42
    a
    0.41
     an
    0.41
    POSITIVE LOGITS
    yscrapers
    0.45
    issi
    0.45
    decor
    0.44
     عادی
    0.44
    akuan
    0.44
    ang
    0.43
     غر
    0.43
    auern
    0.43
    uat
    0.43
    itzt
    0.43
    Act Density 0.003%

    No Known Activations