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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .A
    -0.08
    .↵
    -0.07
    .К
    -0.07
    .П
    -0.07
    .%
    -0.07
    .T
    -0.07
    .^
    -0.07
    .No
    -0.07
    .W
    -0.06
    .M
    -0.06
    POSITIVE LOGITS
     ",
    0.08
     homosexuals
    0.07
    '"
    0.07
    retweeted
    0.07
    們
    0.07
    ediální
    0.07
     ")↵
    0.07
    ")
    0.06
    _present
    0.06
    "-
    0.06
    Act Density 0.304%

    No Known Activations