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

    Neuronpedia

    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =wx
    -0.07
    省份
    -0.07
    )/
    -0.07
     prest
    -0.07
    怀着
    -0.07
    actions
    -0.07
    ):
    -0.07
     kapsam
    -0.07
    _world
    -0.07
    }_{
    -0.07
    POSITIVE LOGITS
    天鹅
    0.07
    风格
    0.07
    .Object
    0.07
     reopening
    0.07
    mpz
    0.06
    什么原因
    0.06
    Ɣ
    0.06
    秋季
    0.06
    agon
    0.06
    flower
    0.06
    Act Density 0.032%

    No Known Activations