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

    Neuronpedia

    INDEX
    Explanations

    negative outcomes or critical states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     évol
    0.43
     nicer
    0.43
     symmetrically
    0.40
     clums
    0.40
    びに
    0.40
     coarser
    0.40
     langfrist
    0.40
     remot
    0.38
     wiser
    0.38
    0.38
    POSITIVE LOGITS
     outright
    0.55
    或
    0.50
    に近い
    0.49
     ಅಥವಾ
    0.49
     partiellement
    0.48
     或
    0.46
     거의
    0.46
     تقريبا
    0.46
    幾乎
    0.45
     или
    0.45
    Act Density 0.237%

    No Known Activations