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

    Neuronpedia

    INDEX
    Explanations

    pronouns and auxiliary verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     who
    -0.07
    Film
    -0.07
    (withDuration
    -0.06
    625
    -0.06
     beaten
    -0.06
     Ihnen
    -0.06
    _contains
    -0.06
    들도
    -0.06
    .parents
    -0.06
    (
↵
    -0.06
    POSITIVE LOGITS
     coherence
    0.06
    ستم
    0.06
     Indonesian
    0.06
    §ظ
    0.06
    imm
    0.06
     categorical
    0.06
    什么
    0.06
     decisions
    0.06
     courseId
    0.06
     První
    0.06
    Act Density 0.064%

    No Known Activations