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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Netflix
    -0.07
     meld
    -0.06
    Officials
    -0.06
     breastfeeding
    -0.06
     lact
    -0.06
    Court
    -0.06
    .ContentType
    -0.06
     planta
    -0.06
    深
    -0.06
    Live
    -0.06
    POSITIVE LOGITS
    مانی
    0.07
    enzyme
    0.07
    译
    0.07
    _pre
    0.07
    Soap
    0.06
    vider
    0.06
    _ylim
    0.06
    둥
    0.06
    ecause
    0.06
     Introduced
    0.06
    Act Density 0.057%

    No Known Activations