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

    Neuronpedia

    INDEX
    Explanations

    Common English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	break
    -0.08
     Battlefield
    -0.07
    Tween
    -0.07
     submodule
    -0.07
     öner
    -0.07
     smiling
    -0.07
    Outer
    -0.06
     infused
    -0.06
    .getIndex
    -0.06
     pipeline
    -0.06
    POSITIVE LOGITS
     Balls
    0.07
    =pk
    0.07
     dernier
    0.06
    ่าการ
    0.06
     quản
    0.06
    国际
    0.06
     casualties
    0.06
    ,UnityEngine
    0.06
     Chun
    0.06
     لا
    0.06
    Act Density 0.017%

    No Known Activations