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

    Neuronpedia

    INDEX
    Explanations

    end markers and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỏng
    0.39
    দিষ্ট
    0.36
    DialogOpen
    0.36
     exfol
    0.35
    ñas
    0.34
    ेंबर
    0.34
    Connor
    0.34
    mimpi
    0.34
     tonnage
    0.34
     peppermint
    0.34
    POSITIVE LOGITS
     END
    0.89
     End
    0.84
    END
    0.84
     end
    0.83
    end
    0.82
    glEnd
    0.74
    End
    0.70
     끝
    0.67
     конец
    0.64
     endif
    0.61
    Act Density 0.055%

    No Known Activations