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

    Neuronpedia

    INDEX
    Explanations

    how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹐
    1.95
     together
    1.93
    }}$$
    1.91
     שלה
    1.89
     both
    1.81
     entrambi
    1.81
     either
    1.79
     this
    1.77
    nets
    1.71
    ysed
    1.71
    POSITIVE LOGITS
    6
    1.83
    7
    1.79
    5
    1.67
    3
    1.62
    4
    1.59
    8
    1.58
    9
    1.57
     строение
    1.36
     Ту
    1.36
    Ка
    1.26
    Act Density 0.000%

    No Known Activations