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

    Neuronpedia

    INDEX
    Explanations

    critical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beach
    -0.07
    帰
    -0.06
     electrode
    -0.06
    .editor
    -0.06
     prism
    -0.06
    پر
    -0.06
    Caption
    -0.06
     vacuum
    -0.06
    _fake
    -0.06
    .clean
    -0.06
    POSITIVE LOGITS
     intermittent
    0.07
     팀
    0.06
    Entity
    0.06
     svým
    0.06
    нин
    0.06
     曰
    0.06
    -rec
    0.06
    ال
    0.06
    itur
    0.06
     endeavors
    0.06
    Act Density 0.810%

    No Known Activations