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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    デ
    -0.06
    Safety
    -0.06
    	animation
    -0.06
     input
    -0.06
     HO
    -0.06
    EXAMPLE
    -0.06
    isher
    -0.06
     PUR
    -0.06
     Gameplay
    -0.06
     homeowner
    -0.05
    POSITIVE LOGITS
     Woodward
    0.07
    чивается
    0.06
     alphabetical
    0.06
     Binder
    0.06
     congr
    0.06
     cca
    0.06
     Fore
    0.06
     Plantae
    0.06
     budou
    0.06
     sniff
    0.06
    Act Density 0.025%

    No Known Activations