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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    现场
    -0.09
     Lia
    -0.08
     evidenced
    -0.08
    美国
    -0.08
     Moll
    -0.08
     Cav
    -0.08
     Chand
    -0.08
     creating
    -0.08
     trat
    -0.07
     Bed
    -0.07
    POSITIVE LOGITS
     الاست
    0.08
     slack
    0.08
     pọ
    0.08
     است
    0.07
    0.07
     outlined
    0.07
    ↵			↵
    0.07
     الإست
    0.07
    rib
    0.07
    -ger
    0.07
    Act Density 0.092%
    No Known Activations