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

    Neuronpedia

    INDEX
    Explanations

    computers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    елен
    -0.07
    _REASON
    -0.07
     Mono
    -0.06
     ARC
    -0.06
    커스
    -0.06
    _SCHED
    -0.06
     masih
    -0.06
    .escape
    -0.06
    276
    -0.06
    Processor
    -0.06
    POSITIVE LOGITS
     《
    0.07
     logically
    0.07
     inefficient
    0.06
     신입
    0.06
     salty
    0.06
    dj
    0.06
     Siber
    0.06
     atte
    0.06
     then
    0.06
     designate
    0.06
    Act Density 0.065%

    No Known Activations