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

    Neuronpedia

    INDEX
    Explanations

    polarization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hunter
    -0.08
    crets
    -0.07
     Bir
    -0.07
     Indiana
    -0.07
    หล
    -0.07
     rais
    -0.07
     McC
    -0.07
     cardio
    -0.06
    ATHER
    -0.06
    那
    -0.06
    POSITIVE LOGITS
     polarization
    0.08
    眼皮
    0.07
    -company
    0.07
    地区
    0.07
    水平
    0.07
     cryptocurrency
    0.07
     sek
    0.07
    #echo
    0.07
    吭
    0.07
     البلد
    0.06
    Act Density 0.007%

    No Known Activations