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

    Neuronpedia

    INDEX
    Explanations

    code loop conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бизнеса
    0.98
     financ
    0.95
     अनेक
    0.85
     khắp
    0.82
     financement
    0.79
     langfrist
    0.79
    <unused676>
    0.79
     pensions
    0.78
    𝘰
    0.78
    𝓂
    0.78
    POSITIVE LOGITS
     является
    1.17
     ہے
    1.09
     indicates
    1.06
     είναι
    1.03
     encapsulates
    1.01
     `<`,
    1.00
     workpiece
    1.00
     cylindrical
    0.99
     denotes
    0.98
     `=`,
    0.96
    Act Density 3.006%

    No Known Activations