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

    Neuronpedia

    INDEX
    Explanations

    oxidation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    입니다
    -0.07
    昨日
    -0.07
    _As
    -0.07
    条件
    -0.06
    (delegate
    -0.06
    .of
    -0.06
     Tanz
    -0.06
    广阔
    -0.06
     agreg
    -0.06
    	command
    -0.06
    POSITIVE LOGITS
    صرف
    0.07
     robotic
    0.07
    עשיר
    0.07
     Per
    0.07
     выпуск
    0.06
     Л
    0.06
    授权
    0.06
     empower
    0.06
     laptops
    0.06
     motivated
    0.06
    Act Density 0.007%

    No Known Activations