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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     funkc
    -0.07
     Vanity
    -0.07
    -Benz
    -0.07
     advertisement
    -0.06
    але
    -0.06
    .sim
    -0.06
    _chain
    -0.06
    -insert
    -0.06
    /her
    -0.06
    pret
    -0.06
    POSITIVE LOGITS
    ög
    0.07
     Muhammed
    0.07
     [~,
    0.06
     endDate
    0.06
     Send
    0.06
    538
    0.06
    ohn
    0.06
     kickoff
    0.06
     =
    0.06
    -----↵
    0.06
    Act Density 0.008%

    No Known Activations