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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gerald
    -0.07
     अग
    -0.06
    ople
    -0.06
     Prometheus
    -0.06
    identify
    -0.06
    .clear
    -0.06
    _https
    -0.06
    fout
    -0.06
    .linkedin
    -0.06
    -city
    -0.06
    POSITIVE LOGITS
     자세
    0.07
     carb
    0.07
     Enforcement
    0.07
    ların
    0.07
     pause
    0.07
     JOptionPane
    0.06
    кав
    0.06
     공지
    0.06
    uais
    0.06
     ·
    0.06
    Act Density 0.075%

    No Known Activations