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

    Neuronpedia

    INDEX
    Explanations

    cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Layout
    -0.08
     дых
    -0.07
     Jad
    -0.06
     efficiently
    -0.06
    .toString
    -0.06
    	Destroy
    -0.06
    _bar
    -0.06
     新
    -0.06
     �
    -0.06
     gameOver
    -0.06
    POSITIVE LOGITS
    -blog
    0.08
    Could
    0.06
     proble
    0.06
    cb
    0.06
    'nde
    0.06
    их
    0.06
     cà
    0.06
     philippines
    0.06
    leo
    0.06
     (?)
    0.06
    Act Density 0.021%

    No Known Activations