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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ();↵↵
    -0.07
    ед
    -0.07
    sockopt
    -0.06
    -enable
    -0.06
     проблема
    -0.06
    -0.06
    лива
    -0.06
    辆
    -0.06
    Có
    -0.06
    анием
    -0.06
    POSITIVE LOGITS
     bạn
    0.07
     Terms
    0.07
     engineered
    0.06
    poke
    0.06
     melanch
    0.06
    _End
    0.06
    	PORT
    0.06
     okam
    0.06
     ram
    0.06
    чис
    0.06
    Act Density 0.001%

    No Known Activations