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

    Neuronpedia

    INDEX
    Explanations

    str/constr (programming)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nichols
    -0.07
     Sach
    -0.07
    集体
    -0.07
    祁
    -0.07
    _reordered
    -0.07
    ꧁
    -0.07
     Said
    -0.07
    金牌
    -0.07
     addChild
    -0.07
    _tools
    -0.06
    POSITIVE LOGITS
    Fly
    0.08
     poderá
    0.07
    sterol
    0.07
     [*
    0.07
    сте
    0.07
     три
    0.07
    bru
    0.07
    ва
    0.07
    باراة
    0.07
    ска
    0.06
    Act Density 0.004%

    No Known Activations