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

    Neuronpedia

    INDEX
    Explanations

    Addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sphere
    -0.06
     LOD
    -0.06
     hak
    -0.06
    .State
    -0.06
     Defined
    -0.06
     WWII
    -0.06
     xi
    -0.06
     thugs
    -0.06
     φ
    -0.05
     suf
    -0.05
    POSITIVE LOGITS
    ;set
    0.07
    rier
    0.07
     Hire
    0.07
    impact
    0.06
     educate
    0.06
     أحمد
    0.06
    -economic
    0.06
     Dem
    0.06
    :r
    0.06
    าง
    0.06
    Act Density 0.019%

    No Known Activations