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

    Neuronpedia

    INDEX
    Explanations

    code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YE
    -0.07
     zaměstn
    -0.07
    Stored
    -0.06
     COST
    -0.06
    اب
    -0.06
     περί
    -0.06
    PLIED
    -0.06
     πά
    -0.06
     fue
    -0.06
    ahat
    -0.06
    POSITIVE LOGITS
     помощи
    0.08
    <path
    0.07
     Histogram
    0.07
    .mobile
    0.07
     других
    0.07
     бізнес
    0.06
     sector
    0.06
     Tech
    0.06
     стар
    0.06
     qq
    0.06
    Act Density 0.001%

    No Known Activations