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

    Neuronpedia

    INDEX
    Explanations

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     seep
    0.79
     drab
    0.77
     baroque
    0.76
     Ideally
    0.76
     percol
    0.75
     indol
    0.75
     disparate
    0.74
     sympathetic
    0.74
     symbi
    0.74
     ke
    0.73
    POSITIVE LOGITS
    9
    0.85
    4
    0.83
    7
    0.82
    ijdens
    0.81
    6
    0.81
    定义
    0.77
    8
    0.76
    čních
    0.75
    इसी
    0.75
    0
    0.74
    Act Density 0.181%

    No Known Activations