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

    Neuronpedia

    INDEX
    Explanations

    ob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Double
    -0.07
    ưở
    -0.07
    uel
    -0.07
    (trans
    -0.07
    Controls
    -0.07
    "In
    -0.07
     Flux
    -0.07
    cess
    -0.07
    澍
    -0.07
     '..
    -0.07
    POSITIVE LOGITS
    /gtest
    0.08
    大楼
    0.07
    眼皮
    0.07
     безопасн
    0.07
    团伙
    0.07
     complaint
    0.07
     hObject
    0.07
    igte
    0.06
    同一
    0.06
     counseling
    0.06
    Act Density 0.004%

    No Known Activations