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

    Neuronpedia

    INDEX
    Explanations

    upper/lower body location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -layer
    -0.06
    she
    -0.06
     Communication
    -0.06
     ingr
    -0.06
     Facilities
    -0.06
    _MOBILE
    -0.06
     diarrhea
    -0.06
    -cols
    -0.06
     popped
    -0.06
     withString
    -0.06
    POSITIVE LOGITS
     Scandin
    0.07
    プラ
    0.06
    ！');↵
    0.06
    MBOL
    0.06
    OKEN
    0.06
    olia
    0.06
    -serif
    0.06
    .FlatAppearance
    0.06
    _plots
    0.06
    avn
    0.06
    Act Density 0.021%

    No Known Activations