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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Capital
    -0.07
     daddy
    -0.07
     smlouvy
    -0.07
     tedy
    -0.07
    archical
    -0.07
    IgnoreCase
    -0.06
    -powered
    -0.06
    icients
    -0.06
    Connection
    -0.06
    693
    -0.06
    POSITIVE LOGITS
    í
    0.07
    OCI
    0.07
     Gri
    0.06
     همین
    0.06
     查看
    0.06
     αυ
    0.06
    iropr
    0.06
     Insider
    0.06
    ivel
    0.06
    checkpoint
    0.06
    Act Density 0.048%

    No Known Activations