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

    Neuronpedia

    INDEX
    Explanations

    advantages and disadvantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Associates
    -0.07
    CellStyle
    -0.07
    ecz
    -0.07
    assignment
    -0.07
    imps
    -0.06
    рой
    -0.06
    _HERSHEY
    -0.06
    imize
    -0.06
    apps
    -0.06
    (latitude
    -0.06
    POSITIVE LOGITS
     Costco
    0.07
    __↵↵
    0.06
     Luxembourg
    0.06
     until
    0.06
     drink
    0.06
    	on
    0.06
     veterans
    0.06
     Restricted
    0.06
    ]=>
    0.06
     litre
    0.06
    Act Density 0.017%

    No Known Activations