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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (serial
    -0.07
    cq
    -0.07
    _published
    -0.07
    variably
    -0.07
    cce
    -0.06
    arkers
    -0.06
     комнат
    -0.06
    ::
    -0.06
    ्पर
    -0.06
     cabinets
    -0.06
    POSITIVE LOGITS
    �
    0.07
     elev
    0.07
    )*/↵
    0.06
    HCI
    0.06
    历史
    0.06
     AUX
    0.06
    coin
    0.06
     phon
    0.06
    lej
    0.06
     SYNC
    0.06
    Act Density 0.004%

    No Known Activations