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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ret
    -0.07
    】↵
    -0.06
     mates
    -0.06
    sheets
    -0.06
    	date
    -0.06
     sharp
    -0.06
    dig
    -0.06
    。この
    -0.06
    	else
    -0.06
    (DATA
    -0.06
    POSITIVE LOGITS
     canActivate
    0.07
     theorem
    0.06
    plr
    0.06
    .scope
    0.06
    Founder
    0.06
     jewel
    0.06
     COUNT
    0.06
     Crew
    0.06
    ื
    0.06
    lobe
    0.06
    Act Density 0.119%

    No Known Activations