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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     panorama
    -0.08
    wcsstore
    -0.08
    �
    -0.07
    📥
    -0.07
     Roku
    -0.07
    🍂
    -0.07
     mobs
    -0.06
    �
    -0.06
    Geo
    -0.06
    볼
    -0.06
    POSITIVE LOGITS
     subtype
    0.08
     father
    0.07
    加强
    0.07
    _refer
    0.07
     Theresa
    0.07
    保障
    0.07
     isize
    0.07
     tend
    0.07
    (te
    0.07
     constexpr
    0.07
    Act Density 0.001%

    No Known Activations