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

    Neuronpedia

    INDEX
    Explanations

    component

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    อาหาร
    -0.07
    NG
    -0.06
    representation
    -0.06
    .Sync
    -0.06
    (Me
    -0.06
     dinosaurs
    -0.06
    ови
    -0.06
    Pos
    -0.06
     minut
    -0.06
     suction
    -0.06
    POSITIVE LOGITS
    -document
    0.08
    (bind
    0.07
     Disconnect
    0.07
     awarded
    0.06
    efully
    0.06
    	main
    0.06
     Tes
    0.06
     adjustment
    0.06
    _window
    0.06
    -top
    0.06
    Act Density 0.002%

    No Known Activations