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

    Neuronpedia

    INDEX
    Explanations

    references for more information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Below
    0.74
     below
    0.71
    below
    0.71
     Below
    0.67
     abaixo
    0.66
     ниже
    0.65
    下面的
    0.64
     abajo
    0.60
    以下の
    0.60
     BELOW
    0.59
    POSITIVE LOGITS
     shown
    0.60
    shown
    0.54
     illustrated
    0.52
     Illustrated
    0.52
    Shown
    0.51
     Shown
    0.51
     depicted
    0.48
    如图
    0.45
    Illustrated
    0.43
    illustrated
    0.42
    Act Density 0.019%

    No Known Activations