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

    Neuronpedia

    INDEX
    Explanations

    the following

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trotz
    0.45
     F
    0.41
     Anders
    0.38
     although
    0.37
     ars
    0.37
     dor
    0.37
     levers
    0.36
     meio
    0.36
     magnetic
    0.35
     Environment
    0.35
    POSITIVE LOGITS
    下記の
    0.49
     aşağıdaki
    0.43
    下面
    0.39
    下記
    0.39
    лії
    0.38
     التالية
    0.38
    0.38
    以下の
    0.37
    下面的
    0.37
    0.37
    Act Density 1.316%

    No Known Activations