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

    Neuronpedia

    INDEX
    Explanations

    European/Eastern European names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Thread
    -0.06
     Maur
    -0.06
     달
    -0.06
     satın
    -0.06
     Brigham
    -0.06
     Fuk
    -0.06
     Raf
    -0.06
    _paths
    -0.06
     få
    -0.05
    Encryption
    -0.05
    POSITIVE LOGITS
     minion
    0.08
    CTIONS
    0.07
    ROT
    0.07
    าช
    0.07
    encers
    0.07
     exact
    0.07
    kos
    0.06
     boarding
    0.06
    <|python_tag|>
    0.06
    CISION
    0.06
    Act Density 0.004%

    No Known Activations