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

    Neuronpedia

    INDEX
    Explanations

    size and length

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    縷
    0.77
    vala
    0.66
    വസ്ഥ
    0.65
    昧
    0.65
    yawa
    0.65
    ందరు
    0.64
     Lamar
    0.61
    ชีพ
    0.60
     especialistas
    0.59
     Verbindung
    0.59
    POSITIVE LOGITS
     size
    2.97
     Size
    2.89
    Size
    2.84
     sizes
    2.72
    size
    2.65
     sized
    2.52
    sized
    2.48
     Sizes
    2.45
     tamaño
    2.44
     larger
    2.42
    Act Density 2.171%

    No Known Activations