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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     engagement
    -0.07
     questionable
    -0.07
     newcomer
    -0.07
    时间
    -0.07
    Initialized
    -0.06
     Introduction
    -0.06
     اختیار
    -0.06
     unusual
    -0.06
     unfavorable
    -0.06
    .AddComponent
    -0.06
    POSITIVE LOGITS
    _JOB
    0.07
    '}↵↵
    0.06
    ấn
    0.06
    аніз
    0.06
    elight
    0.06
    ?>'
    0.06
    _mirror
    0.06
     fkk
    0.06
    iferay
    0.06
    ↵
↵
↵
    0.06
    Act Density 0.037%

    No Known Activations