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

    Neuronpedia

    INDEX
    Explanations

    arbitr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (!$
    -0.07
    ifica
    -0.07
    .'.$
    -0.07
    กฎหมาย
    -0.06
    etas
    -0.06
    elist
    -0.06
    .St
    -0.06
    álním
    -0.06
    	st
    -0.06
     weekdays
    -0.06
    POSITIVE LOGITS
     arbitr
    0.07
     equip
    0.07
     accessible
    0.07
     نويسنده
    0.07
    .linear
    0.07
     Older
    0.06
     define
    0.06
     educated
    0.06
     Defined
    0.06
    eterminate
    0.06
    Act Density 0.001%

    No Known Activations