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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utura
    -0.07
    iolet
    -0.07
    .getContentPane
    -0.07
    	TR
    -0.06
    ấm
    -0.06
     เอ
    -0.06
    ி
    -0.06
    /interface
    -0.06
     Knife
    -0.06
    ็นอ
    -0.06
    POSITIVE LOGITS
     kür
    0.08
     прот
    0.07
    Argb
    0.06
     text
    0.06
     البل
    0.06
     usr
    0.06
    變
    0.06
    bomb
    0.06
     commit
    0.06
    .isLoggedIn
    0.06
    Act Density 0.015%

    No Known Activations