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

    Neuronpedia

    INDEX
    Explanations

    powering up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lament
    -0.08
     covered
    -0.08
     طن
    -0.08
    ٹو
    -0.08
    Telephone
    -0.08
     обслуж
    -0.08
    verkehr
    -0.08
     санитар
    -0.08
     rundt
    -0.08
     Coverage
    -0.08
    POSITIVE LOGITS
    -enh
    0.11
     boosts
    0.11
    提升
    0.11
    Boost
    0.11
     Boost
    0.11
     upgrade
    0.10
     upgrades
    0.10
     boost
    0.10
    boost
    0.10
     enhancement
    0.10
    Act Density 0.033%

    No Known Activations