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

    Neuronpedia

    INDEX
    Explanations

    Scientific observations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (opts
    -0.08
    itize
    -0.07
     hateful
    -0.07
    dry
    -0.07
    cash
    -0.07
    	print
    -0.06
    แจ
    -0.06
     �
    -0.06
    -Ch
    -0.06
     stealth
    -0.06
    POSITIVE LOGITS
     legacy
    0.06
    _mov
    0.06
    \Entities
    0.06
     Lottery
    0.06
    apGestureRecognizer
    0.06
     downtime
    0.06
     refresh
    0.06
     Zelda
    0.06
    alığı
    0.06
     extents
    0.06
    Act Density 0.006%

    No Known Activations