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

    Neuronpedia

    INDEX
    Explanations

    под

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chains
    -0.07
    	e
    -0.06
     harmony
    -0.06
     privilege
    -0.06
     egret
    -0.06
    ladık
    -0.06
    	with
    -0.06
     河
    -0.06
    RB
    -0.06
    341
    -0.06
    POSITIVE LOGITS
     под
    0.12
     Sous
    0.09
     під
    0.09
     تحت
    0.08
     sous
    0.08
    од
    0.08
     MongoClient
    0.08
     Под
    0.08
     sotto
    0.07
    Под
    0.07
    Act Density 0.009%

    No Known Activations