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

    Neuronpedia

    INDEX
    Explanations

    Day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chatt
    -0.06
     insists
    -0.06
     처
    -0.06
    metis
    -0.06
     Clan
    -0.06
    RH
    -0.06
     seem
    -0.05
     sprinkle
    -0.05
     flips
    -0.05
    _kill
    -0.05
    POSITIVE LOGITS
     */↵↵↵
    0.07
     Mandela
    0.07
    _DESCRIPTION
    0.07
     Bosnia
    0.07
     mapView
    0.07
    -package
    0.07
    }()↵↵
    0.06
     зн
    0.06
     USER
    0.06
    	onClick
    0.06
    Act Density 0.000%

    No Known Activations