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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ')]
    -0.07
    콘
    -0.07
     NTN
    -0.07
     lowered
    -0.06
     laundry
    -0.06
    ระเบ
    -0.06
     REG
    -0.06
     Addresses
    -0.06
     stuff
    -0.06
     seminal
    -0.06
    POSITIVE LOGITS
    /www
    0.07
     піш
    0.07
    ZW
    0.06
    JK
    0.06
    Jake
    0.06
    ictureBox
    0.06
    esy
    0.06
    Ste
    0.06
     Exclude
    0.06
    Restart
    0.06
    Act Density 0.105%

    No Known Activations