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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     пенс
    -0.06
    Tracker
    -0.06
    申博
    -0.06
     dildo
    -0.06
     desire
    -0.06
    ंतर
    -0.06
     προς
    -0.06
    \Notifications
    -0.06
     Twitch
    -0.05
    	canvas
    -0.05
    POSITIVE LOGITS
     професій
    0.07
     terrified
    0.06
     시작
    0.06
     steht
    0.06
     Sequential
    0.06
    .expires
    0.06
     dg
    0.06
     fairly
    0.06
    싸
    0.06
    mrt
    0.06
    Act Density 0.049%

    No Known Activations