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

    Neuronpedia

    INDEX
    Explanations

    everything except

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    许多
    1.32
    許多
    1.28
    Often
    1.21
     अक्सर
    1.19
     многих
    1.18
    often
    1.11
     muitas
    1.10
     ofta
    1.10
    某些
    1.10
    更多
    1.09
    POSITIVE LOGITS
     except
    2.44
    except
    2.03
     Except
    1.95
     excepto
    1.93
     including
    1.88
     excepting
    1.87
     EXCEPT
    1.85
     kecuali
    1.70
     sauf
    1.61
    Except
    1.57
    Act Density 0.191%

    No Known Activations