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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    FormattedMessage
    -0.07
     огранич
    -0.07
     Pvt
    -0.07
     atte
    -0.07
     změn
    -0.07
    ctime
    -0.07
    ENG
    -0.07
     Rus
    -0.07
     Transmission
    -0.07
    POSITIVE LOGITS
    0.08
     Gray
    0.08
    0.07
    0.07
     Ever
    0.07
    0.07
     kami
    0.07
     그래
    0.07
    .todo
    0.07
    0.06
    Act Density 0.007%

    No Known Activations