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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PosY
    -0.07
     Pilot
    -0.07
    	Y
    -0.06
     troops
    -0.06
     Tues
    -0.06
     الات
    -0.06
     fø
    -0.06
     muj
    -0.06
     Libya
    -0.06
    ền
    -0.06
    POSITIVE LOGITS
     swallowed
    0.07
     Papers
    0.07
     exposed
    0.07
    %!
    0.07
     capita
    0.07
    ribly
    0.07
     Coconut
    0.07
    *out
    0.06
    DECLARE
    0.06
     dissolve
    0.06
    Act Density 0.002%

    No Known Activations