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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ray
    -0.07
     fucks
    -0.06
     обст
    -0.06
    adık
    -0.06
     Freak
    -0.06
    )%
    -0.06
    dest
    -0.06
    #[
    -0.06
     Halk
    -0.06
    yes
    -0.06
    POSITIVE LOGITS
     sinful
    0.07
    BagConstraints
    0.07
    {}\
    0.07
     kickoff
    0.07
    농
    0.06
     Aub
    0.06
    .AllowUser
    0.06
     Arlington
    0.06
     peaceful
    0.06
    /order
    0.06
    Act Density 0.004%

    No Known Activations