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

    Neuronpedia

    INDEX
    Explanations

    has long been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    现在的
    0.49
    엊
    0.48
     empie
    0.47
    今の
    0.45
     başladı
    0.45
     empezó
    0.45
     empiezan
    0.44
     empieza
    0.44
     തുടങ്ങി
    0.44
    VOR
    0.43
    POSITIVE LOGITS
     historically
    1.30
     traditionally
    1.09
     Historically
    0.97
    Historically
    0.93
    histor
    0.85
     histó
    0.82
     repeatedly
    0.82
     Traditionally
    0.81
     longstanding
    0.77
    Traditionally
    0.76
    Act Density 0.022%

    No Known Activations