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

    Neuronpedia

    INDEX
    Explanations

    mitigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    스토
    -0.08
    /signup
    -0.07
     guarante
    -0.06
    梦
    -0.06
    范围
    -0.06
    icamente
    -0.06
    виж
    -0.06
     Elle
    -0.06
     v�
    -0.06
    數
    -0.06
    POSITIVE LOGITS
    !!,
    0.07
     Buck
    0.06
    .Wh
    0.06
     additional
    0.06
    	controller
    0.06
    itime
    0.06
     Asked
    0.06
    escal
    0.06
    -derived
    0.06
    ทาง
    0.06
    Act Density 0.089%

    No Known Activations