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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     compounds
    -0.07
     thunk
    -0.07
     coded
    -0.07
     DEA
    -0.07
     dt
    -0.06
    Guard
    -0.06
     weeks
    -0.06
    暮
    -0.06
     Game
    -0.06
     coff
    -0.06
    POSITIVE LOGITS
    каз
    0.07
    (pg
    0.06
     welcomes
    0.06
    (sid
    0.06
     refurb
    0.06
    .GetService
    0.06
    	RTDBG
    0.06
     PageInfo
    0.06
     inevitable
    0.06
    .Current
    0.06
    Act Density 0.008%

    No Known Activations