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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ±ظ
    -0.07
     Sharia
    -0.07
     Sır
    -0.07
     Hannity
    -0.06
     kurulan
    -0.06
    .paper
    -0.06
     Kadın
    -0.06
     ego
    -0.06
     FR
    -0.06
     Ả
    -0.06
    POSITIVE LOGITS
    "][
    0.07
     devoted
    0.06
    obl
    0.06
    .↵↵
    0.06
    extra
    0.06
     believes
    0.06
    Exercise
    0.06
     restart
    0.06
    。↵↵
    0.06
    LEM
    0.06
    Act Density 0.007%

    No Known Activations