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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deployment
    -0.07
     ofType
    -0.07
    \Base
    -0.07
     optimizing
    -0.07
     Scheduled
    -0.07
     Resume
    -0.07
     AGE
    -0.06
     trajectory
    -0.06
     По
    -0.06
    commerce
    -0.06
    POSITIVE LOGITS
    弥
    0.07
    ัพย
    0.07
    _lcd
    0.06
    +="
    0.06
     поврежд
    0.06
     eleştir
    0.06
     επα
    0.06
    alu
    0.06
    áč
    0.06
     "\""
    0.06
    Act Density 0.006%

    No Known Activations