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

    Neuronpedia

    INDEX
    Explanations

    import css

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    摩擦
    0.44
     सलाद
    0.43
     바꿔
    0.42
    Elementos
    0.42
     Sorrow
    0.42
    বলী
    0.42
    ススメ
    0.42
    উঠ
    0.41
    কেশ
    0.41
    屶
    0.41
    POSITIVE LOGITS
     functional
    0.54
    functional
    0.50
    function
    0.49
     '
    0.46
     function
    0.46
    …
    0.43
     ('
    0.43
     ‘
    0.41
     …
    0.40
    ;
    0.40
    Act Density 0.000%

    No Known Activations