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
    .Health
    -0.07
    	Common
    -0.07
    _profit
    -0.07
    AIM
    -0.07
    -East
    -0.07
     Comfort
    -0.07
     Shut
    -0.06
    omatic
    -0.06
     один
    -0.06
    璠
    -0.06
    POSITIVE LOGITS
    칕
    0.07
     pd
    0.07
     wom
    0.07
    蹀
    0.06
     стен
    0.06
    ının
    0.06
    领军
    0.06
    ಪ
    0.06
    槊
    0.06
     tv
    0.06
    Act Density 0.177%

    No Known Activations