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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clean
    -0.07
     民
    -0.07
     remedies
    -0.07
    .AbsoluteConstraints
    -0.07
    Main
    -0.06
     voting
    -0.06
     hero
    -0.06
     корм
    -0.06
     applicants
    -0.06
     miles
    -0.06
    POSITIVE LOGITS
     را
    0.08
     SWAT
    0.07
     日期
    0.07
    _episode
    0.07
    added
    0.06
     DbContext
    0.06
     ud
    0.06
    버전
    0.06
    ฟ
    0.06
    -message
    0.06
    Act Density 0.008%

    No Known Activations