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

    Neuronpedia

    INDEX
    Explanations

    code variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :convert
    -0.07
    ≧
    -0.07
     Insights
    -0.06
    _READY
    -0.06
     sf
    -0.06
     Bro
    -0.06
     kata
    -0.06
    _even
    -0.06
     Negro
    -0.06
     '';
    -0.06
    POSITIVE LOGITS
     quiere
    0.06
    ividad
    0.06
     nostra
    0.06
    */↵↵↵
    0.06
     ilk
    0.06
    ocratic
    0.06
     guiActive
    0.06
     إذا
    0.06
    TEGER
    0.06
    	select
    0.05
    Act Density 0.010%

    No Known Activations