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

    Neuronpedia

    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mp
    -0.07
    อดภ
    -0.07
     Series
    -0.07
    Tip
    -0.07
    752
    -0.07
     clean
    -0.07
     calls
    -0.07
     primitives
    -0.07
     focuses
    -0.07
    .translate
    -0.06
    POSITIVE LOGITS
     parlament
    0.07
     Comey
    0.07
    刚才
    0.06
     Tây
    0.06
    ѓ
    0.06
     escort
    0.06
    хран
    0.06
    rient
    0.06
    .StringUtils
    0.06
     Soviets
    0.06
    Act Density 0.057%

    No Known Activations