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

    Neuronpedia

    INDEX
    Explanations

    contend/end

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     of
    -0.08
     dấu
    -0.07
    动物园
    -0.07
    inux
    -0.07
    _IR
    -0.07
     My
    -0.07
    奄
    -0.07
    Shapes
    -0.07
    泣
    -0.07
     lửa
    -0.07
    POSITIVE LOGITS
    Neill
    0.07
     lending
    0.07
    =>{↵
    0.07
    -going
    0.07
    trying
    0.07
    说
    0.07
     tùy
    0.07
    ':{'
    0.07
     elsif
    0.07
    קרקע
    0.07
    Act Density 0.003%

    No Known Activations