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

    Neuronpedia

    INDEX
    Explanations

    studies, medical records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (FILE
    -0.07
    oto
    -0.07
    飞跃
    -0.07
    owler
    -0.07
     TJ
    -0.07
    そうだ
    -0.07
     Stream
    -0.06
    	fd
    -0.06
    \Service
    -0.06
     Dre
    -0.06
    POSITIVE LOGITS
    任何
    0.07
    geme
    0.07
    רן
    0.06
    然后再
    0.06
     eben
    0.06
     any
    0.06
     usted
    0.06
    บน
    0.06
     أخرى
    0.06
    .attributes
    0.06
    Act Density 0.032%

    No Known Activations