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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ugi
    -0.26
    âĪļ
    -0.26
    ERC
    -0.25
     streamlined
    -0.25
    ág
    -0.24
    uber
    -0.24
     najwyższ
    -0.24
    arti
    -0.24
    erc
    -0.24
    o
    -0.24
    POSITIVE LOGITS
    intage
    0.28
    éĵĥ
    0.25
     Michele
    0.25
    涵
    0.25
     Chall
    0.25
    éĺµ
    0.25
    som
    0.24
    iband
    0.24
    igm
    0.24
    _orient
    0.24
    Act Density 3.580%

    No Known Activations