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

    Neuronpedia

    INDEX
    Explanations

    main model component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Profiles
    -0.07
    (ship
    -0.06
     없음
    -0.06
    _CLI
    -0.06
    -С
    -0.06
     solvent
    -0.06
    /')↵
    -0.06
    Interview
    -0.06
    ภาพยนตร
    -0.06
     inherits
    -0.06
    POSITIVE LOGITS
    Bug
    0.07
     ViewGroup
    0.06
     lat
    0.06
    morgan
    0.06
    	function
    0.06
     gent
    0.06
    permanent
    0.06
    ike
    0.06
    алось
    0.06
     Zum
    0.06
    Act Density 0.233%

    No Known Activations