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

    Neuronpedia

    INDEX
    Explanations

    Through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olding
    -0.07
     Starbucks
    -0.07
     Magnum
    -0.06
    "B
    -0.06
     OVERRIDE
    -0.06
     paging
    -0.06
    (Book
    -0.06
    istr
    -0.06
    opus
    -0.06
    -sk
    -0.06
    POSITIVE LOGITS
    ApiKey
    0.07
     LiveData
    0.06
     Assess
    0.06
    ife
    0.06
    tie
    0.06
     inning
    0.06
    UserRole
    0.06
    RetVal
    0.06
                
    0.06
    圍
    0.06
    Act Density 0.075%

    No Known Activations