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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hawk
    -0.08
     začal
    -0.06
     začala
    -0.06
     satin
    -0.06
    Bank
    -0.06
     nacional
    -0.06
    ús
    -0.06
     qued
    -0.06
    -state
    -0.06
     traff
    -0.06
    POSITIVE LOGITS
    ラン
    0.07
    方法
    0.06
     geschichten
    0.06
     бур
    0.06
    SELECT
    0.06
    reducers
    0.06
     QTimer
    0.06
    FileNotFoundException
    0.06
     randomness
    0.06
    irtschaft
    0.06
    Act Density 0.046%

    No Known Activations