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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     cmdline
    -0.06
     lange
    -0.06
     그
    -0.06
     Yad
    -0.06
    館
    -0.06
    っ
    -0.06
    lla
    -0.06
     lil
    -0.06
     Versions
    -0.06
    POSITIVE LOGITS
    icontrol
    0.07
     Worce
    0.07
     และ
    0.06
    acie
    0.06
     Cosmetic
    0.06
     onBackPressed
    0.06
    elper
    0.06
     Melania
    0.06
    _Info
    0.06
     stør
    0.06
    Act Density 0.057%

    No Known Activations