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

    Neuronpedia

    INDEX
    Explanations

    alternating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    licenses
    -0.08
     Consultant
    -0.07
    CENT
    -0.07
     sesso
    -0.07
    Extensions
    -0.07
     NATIONAL
    -0.07
    cuts
    -0.07
    <Class
    -0.07
    签
    -0.07
    .inc
    -0.06
    POSITIVE LOGITS
     unitOfWork
    0.07
    ϐ
    0.07
     ADHD
    0.07
     TERM
    0.07
     Omega
    0.07
    🍁
    0.07
    课文
    0.07
    .tensor
    0.06
     LOVE
    0.06
     Thou
    0.06
    Act Density 0.011%

    No Known Activations