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

    Neuronpedia

    INDEX
    Explanations

    object comparison and duplication methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    絝
    -1.87
     entrenamiento
    -1.80
    -1.77
    矬
    -1.77
    袛
    -1.75
     pierws
    -1.74
    媪
    -1.73
    蓠
    -1.72
    -1.72
     mamy
    -1.70
    POSITIVE LOGITS
    '
    2.28
    8
    2.14
    2
    2.13
     for
    1.82
    3
    1.80
    1
    1.79
    4
    1.75
    7
    1.73
    when
    1.73
    6
    1.66
    Act Density 0.005%

    No Known Activations