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

    Neuronpedia

    INDEX
    Explanations

    mid

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Asia
    -0.08
     Billy
    -0.06
     king
    -0.06
     Updates
    -0.06
     Markets
    -0.06
    iment
    -0.06
     VPN
    -0.06
     :]
    -0.06
     Carry
    -0.06
    Politics
    -0.06
    POSITIVE LOGITS
     kurtul
    0.07
    สนาม
    0.07
     değiş
    0.07
    觉得
    0.06
    itioner
    0.06
    /******/
    0.06
     webinar
    0.06
    (operation
    0.06
     Да
    0.06
    /ge
    0.06
    Act Density 0.114%

    No Known Activations