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

    Neuronpedia

    INDEX
    Explanations

    regex quantifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peters
    -0.07
    生素
    -0.07
     Dion
    -0.07
     Lens
    -0.07
     dildo
    -0.07
     historically
    -0.07
    Ion
    -0.07
    钢琴
    -0.07
     Joel
    -0.07
     einz
    -0.07
    POSITIVE LOGITS
     queens
    0.07
     מציע
    0.07
     negotiations
    0.07
    ⊋
    0.07
    귀
    0.06
    _eng
    0.06
    מדה
    0.06
    informatics
    0.06
     breed
    0.06
    已达
    0.06
    Act Density 0.001%

    No Known Activations