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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Double
    -0.07
     населення
    -0.07
     RX
    -0.07
    れて
    -0.06
    _reservation
    -0.06
    imité
    -0.06
     Pastor
    -0.06
    ово
    -0.06
     хв
    -0.06
    ESSAGE
    -0.06
    POSITIVE LOGITS
    306
    0.06
    _RANGE
    0.06
     однако
    0.06
    avatars
    0.06
     sought
    0.05
    -custom
    0.05
     Schw
    0.05
    130
    0.05
    UGHT
    0.05
    chs
    0.05
    Act Density 0.030%

    No Known Activations