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

    Neuronpedia

    INDEX
    Explanations

    Please

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pruning
    -0.06
    wd
    -0.06
    ancode
    -0.06
    кид
    -0.06
    nature
    -0.06
     könnte
    -0.06
    ปล
    -0.06
    avour
    -0.06
     Наз
    -0.06
    energy
    -0.06
    POSITIVE LOGITS
    <unsigned
    0.07
     dispatcher
    0.07
     accredited
    0.07
    .OPEN
    0.06
     افت
    0.06
     baff
    0.06
    ATIONS
    0.06
    ificates
    0.06
     elektr
    0.06
    '),↵↵
    0.06
    Act Density 0.047%

    No Known Activations