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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tweet
    -0.08
    Ana
    -0.07
    Thr
    -0.07
    撮
    -0.07
     ат
    -0.07
    Performed
    -0.07
    �
    -0.07
    خب
    -0.06
    walk
    -0.06
    	sp
    -0.06
    POSITIVE LOGITS
     Phys
    0.07
    nze
    0.07
    leanup
    0.06
     myself
    0.06
    game
    0.06
     down
    0.06
     stopped
    0.06
     themselves
    0.06
     influencers
    0.06
    님
    0.06
    Act Density 0.001%

    No Known Activations