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

    Neuronpedia

    INDEX
    Explanations

    References

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    allis
    -0.06
     faucet
    -0.06
     gee
    -0.06
     WANT
    -0.06
     Lamar
    -0.06
     pioneering
    -0.06
    ("__
    -0.05
     stringify
    -0.05
     CONNECT
    -0.05
    .For
    -0.05
    POSITIVE LOGITS
    amilia
    0.08
    ,tr
    0.07
     Você
    0.07
    ?]
    0.07
    The
    0.07
    _um
    0.07
     adel
    0.07
    ;m
    0.07
    \:
    0.07
    "]))↵
    0.07
    Act Density 0.002%

    No Known Activations