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

    Neuronpedia

    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McCoy
    -0.06
     errorHandler
    -0.06
     Mayer
    -0.06
     MA
    -0.06
     sched
    -0.06
    words
    -0.06
    ollah
    -0.06
    realm
    -0.06
     FileWriter
    -0.06
    anno
    -0.06
    POSITIVE LOGITS
    UAGE
    0.06
     Southern
    0.06
    Southern
    0.06
     επ
    0.06
    antage
    0.06
    hower
    0.06
     fict
    0.06
    (ship
    0.06
     rear
    0.06
    odox
    0.06
    Act Density 0.001%

    No Known Activations