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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defe
    -0.07
     зуб
    -0.06
     �
    -0.06
     Miss
    -0.06
     الأم
    -0.06
    bows
    -0.06
    母
    -0.06
    ��
    -0.06
    親
    -0.06
     DataFrame
    -0.06
    POSITIVE LOGITS
    о
    0.07
     inevitable
    0.06
    tod
    0.06
    artment
    0.06
     imply
    0.06
     identifiable
    0.06
    ượt
    0.06
     insure
    0.06
    Published
    0.06
    ennes
    0.06
    Act Density 0.000%

    No Known Activations