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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations and their meanings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ()'
    -0.06
    秘
    -0.06
    SCORE
    -0.06
     migrating
    -0.06
     doubly
    -0.06
     ragaz
    -0.06
    olph
    -0.06
     Sloven
    -0.06
     geen
    -0.06
     BO
    -0.06
    POSITIVE LOGITS
    iến
    0.07
    WithContext
    0.07
    يكي
    0.07
    boost
    0.07
    (connectionString
    0.06
    /as
    0.06
    soap
    0.06
    _PULL
    0.06
    哥
    0.06
    ніверсит
    0.06
    Act Density 0.007%

    No Known Activations