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

    Neuronpedia

    INDEX
    Explanations

    training and procedures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     publicly
    -0.07
     merely
    -0.06
    シュ
    -0.06
     aire
    -0.06
    DEST
    -0.06
    FLASH
    -0.06
    лян
    -0.06
     condemning
    -0.06
    obbled
    -0.06
    haven
    -0.06
    POSITIVE LOGITS
    CRC
    0.07
     nek
    0.07
     Phill
    0.06
     (--
    0.06
     strokeLine
    0.06
    )(_
    0.06
    _runner
    0.06
    chází
    0.06
     creepy
    0.06
    ()*
    0.06
    Act Density 0.070%

    No Known Activations