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
     Platinum
    -0.07
     nin
    -0.06
    sticks
    -0.06
    �n
    -0.06
     spit
    -0.06
     countless
    -0.06
     мав
    -0.06
     FD
    -0.06
    ')[
    -0.06
    =[
    -0.05
    POSITIVE LOGITS
    ดย
    0.08
     illum
    0.07
     黄
    0.07
    atype
    0.07
    �이
    0.07
    อส
    0.07
     ไทย
    0.06
     文
    0.06
    .addSubview
    0.06
     刘
    0.06
    Act Density 0.006%

    No Known Activations